case-based recommender systems for personalized finance advisory

120
Cataldo Musto, Giovanni Semeraro Case-based Recommender Systems for Personalized Finance Advisory Graz (Austria) - 16.04.2015

Upload: cataldo-musto

Post on 15-Jul-2015

264 views

Category:

Technology


0 download

TRANSCRIPT

Page 1: Case-based Recommender Systems for Personalized Finance Advisory

Cataldo Musto, Giovanni Semeraro

Case-based Recommender Systems for Personalized Finance Advisory

Graz (Austria) - 16.04.2015

Page 2: Case-based Recommender Systems for Personalized Finance Advisory

one minute on the Web

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 3: Case-based Recommender Systems for Personalized Finance Advisory

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 4: Case-based Recommender Systems for Personalized Finance Advisory

we can handle 126 bits of information we deal with 393 bits of information

ratio: more than 3x(Source: Adrian C.Ott, The 24-hour customer)

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 5: Case-based Recommender Systems for Personalized Finance Advisory

(from Matrix)

decision-making is actually challenging

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 6: Case-based Recommender Systems for Personalized Finance Advisory

paradox of choice(Barry Schwartz, TED talk “Why more is less”)

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 7: Case-based Recommender Systems for Personalized Finance Advisory

(financial) overloadC.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 8: Case-based Recommender Systems for Personalized Finance Advisory

solution: personalizationC.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 9: Case-based Recommender Systems for Personalized Finance Advisory

to adapt asset portfolios

on the ground of personal user profile and needs

Insight:

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 10: Case-based Recommender Systems for Personalized Finance Advisory

SolutionRecommender Systems

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 11: Case-based Recommender Systems for Personalized Finance Advisory

Recommender Systems

Relevant items (movies, news, books, etc.) are suggested to the user according to her preferences.

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 12: Case-based Recommender Systems for Personalized Finance Advisory

definitionRecommender Systems have the goal of guiding the

users in a personalized way to interesting

or useful objects in a large space of possible options.

Burke, 2002 (*)(*) Robin D. Burke: Hybrid Recommender Systems: Survey and Experiments. UMUAI, volume 12, issue 4, 331-370 (2002)

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 13: Case-based Recommender Systems for Personalized Finance Advisory

does it fit our scenario?“we are leaving the age of information, we are entering the age of recommendation”

(C.Anderson, The Long Tail. Wired. October 2004)

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 14: Case-based Recommender Systems for Personalized Finance Advisory

Recommender Systems

“[...] The technology is used by shopping websites such as Amazon, which receives about 35 percent of its revenue via product recommendations. It is also used by coupon sites like Groupon; by travel sites to suggest flights, hotels, and rental cars; by social-networking sites such as LinkedIn; by video sites like Netflix to recommend movies and TV shows, and by music, news, and food sites to suggest songs, news stories, and restaurants, respectively. Even financial-services firms recently began using recommender systems to provide alerts for investors about key market events in which they might be interested”

(N.Leavitt, “A technology that comes highly recommended” - http://tinyurl.com/d5y5hyl)

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 15: Case-based Recommender Systems for Personalized Finance Advisory

Recommender Systemsfinancial services

http://www.bloomberg.com/news/articles/2015-03-16/smart-beta-etfs-attract-billions-with-critics-blaming-dumb-money

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 16: Case-based Recommender Systems for Personalized Finance Advisory

Recommender Systemssuccess stories

“People who bought…”on Amazon

“Discover”on Spotify

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 17: Case-based Recommender Systems for Personalized Finance Advisory

Recommender SystemsRecommender Systemsunexpected stories

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 18: Case-based Recommender Systems for Personalized Finance Advisory

Recommender SystemsRecommender Systemsunexpected stories

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 19: Case-based Recommender Systems for Personalized Finance Advisory

Recommender SystemsRecommender Systemsunexpected stories

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 20: Case-based Recommender Systems for Personalized Finance Advisory

Recommender SystemsRecommender Systemsunexpected stories

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 21: Case-based Recommender Systems for Personalized Finance Advisory

recommending financial products is a complex task

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 22: Case-based Recommender Systems for Personalized Finance Advisory

flocking

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 23: Case-based Recommender Systems for Personalized Finance Advisory

flocking

Too many users could be moved towards the same suggestions

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 24: Case-based Recommender Systems for Personalized Finance Advisory

flocking

consequence: price manipulation (as in trader forums)

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 25: Case-based Recommender Systems for Personalized Finance Advisory

poor knowledge

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 26: Case-based Recommender Systems for Personalized Finance Advisory

Features describing both assets classes and private investors are

poorly meaningful

poor knowledge

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 27: Case-based Recommender Systems for Personalized Finance Advisory

poor history

A combination of asset classes is typically kept for a long time

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 28: Case-based Recommender Systems for Personalized Finance Advisory

Solution

Case-based Recommender SystemsC.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 29: Case-based Recommender Systems for Personalized Finance Advisory

case-based RSs• Inspired by case-based reasoning

• Similar problems solved in the past are used as knowledge base

• Reasoning by analogy

• The recommendation process relies on the retrieval and the adaptation of the solutions adopted to solve similar cases

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 30: Case-based Recommender Systems for Personalized Finance Advisory

....butwhat do we actually mean with ‘case’ ?

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 31: Case-based Recommender Systems for Personalized Finance Advisory

case base

• A case is a the formalization of a previously solved problem

• In our setting

• Description of a user

• Description of a portfolio

• An evaluation of the proposed solution

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 32: Case-based Recommender Systems for Personalized Finance Advisory

case-baseexample

user solution evaluation

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 33: Case-based Recommender Systems for Personalized Finance Advisory

case-baseexample

user solution evaluation

User Features Risk Profile: LowFinancial Experience: HighFinancial Situation: Very HighInvestment Goals: MediumTemporal Goals: Medium

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 34: Case-based Recommender Systems for Personalized Finance Advisory

case-baseexample

user solution evaluation

User Features Risk Profile: LowFinancial Experience: HighFinancial Situation: Very HighInvestment Goals: MediumTemporal Goals: Medium

Euro Bonds 30%

High-Yield Bonds 10%

Fixed-Rate bonds 22%

Euro Stocks 23%

Emerging Market Stocks 7%

Money Market 8%

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 35: Case-based Recommender Systems for Personalized Finance Advisory

case-baseexample

user solution evaluation

User Features Risk Profile: LowFinancial Experience: HighFinancial Situation: Very HighInvestment Goals: MediumTemporal Goals: Medium

monthly rate (e.g.)

+0.22%

Euro Bond 30%

High-Yield Bonds 10%

Fixed-Rate bonds 22%

Euro Stocks 23%

Emerging Markets Stocks 7%

Money Market 8%

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 36: Case-based Recommender Systems for Personalized Finance Advisory

case-based RSssolving cycle

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 37: Case-based Recommender Systems for Personalized Finance Advisory

case-based reasoning for personalized wealth management

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 38: Case-based Recommender Systems for Personalized Finance Advisory

scenario

“Scrooge McDuck wants to get richer. He decided to invest some of his savings and he asked for help to a

financial advisor”

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 39: Case-based Recommender Systems for Personalized Finance Advisory

step 1 user modeling

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 40: Case-based Recommender Systems for Personalized Finance Advisory

scenario

Which features may describe

Scrooge McDuck?

step 1

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 41: Case-based Recommender Systems for Personalized Finance Advisory

scenario

User Features Risk Profile: Low

Investment Horizon HighInvestment Experience Very High

Investment Goals: MediumFinancial Assets: Medium

step 1

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 42: Case-based Recommender Systems for Personalized Finance Advisory

User Features Risk Profile: Low

Investment Horizon HighInvestment Experience Very High

Investment Goals: MediumFinancial Assets: Medium

scenario

MiFID-based

step 1

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 43: Case-based Recommender Systems for Personalized Finance Advisory

scenariostep 1

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

+Generic Demographical Features

User Features Risk Profile: Low

Investment Horizon HighInvestment Experience Very High

Investment Goals: MediumFinancial Assets: Medium

Page 44: Case-based Recommender Systems for Personalized Finance Advisory

in a classical pipeline, the target user

would have received a “model” portfolio tailored on her profile

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 45: Case-based Recommender Systems for Personalized Finance Advisory

in a pipeline fostered by a recommender system, the financial advisor can analyze the portfolios proposed to similar users

to tailor the proposal

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 46: Case-based Recommender Systems for Personalized Finance Advisory

step 2 neighbors identification

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 47: Case-based Recommender Systems for Personalized Finance Advisory

given a case base, it is necessary to

define a similarity measure to compute how similar two cases are

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 48: Case-based Recommender Systems for Personalized Finance Advisory

neighbors identificationtrivial similarity: user match

two cases are similar if they share exactly the same features

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 49: Case-based Recommender Systems for Personalized Finance Advisory

trivial similarity: user match

two cases are similar if they share exactly the same features

neighbors identification

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 50: Case-based Recommender Systems for Personalized Finance Advisory

neighbors identification

cases are represented as points in a vector space

geometrical alternative: cosine similarity

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 51: Case-based Recommender Systems for Personalized Finance Advisory

geometrical representationC.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 52: Case-based Recommender Systems for Personalized Finance Advisory

geometrical alternative: cosine similarityneighbors identification

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 53: Case-based Recommender Systems for Personalized Finance Advisory

case-based RSsgeometrical alternative: cosine similarity

each case is seen as a vector

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 54: Case-based Recommender Systems for Personalized Finance Advisory

case-based RSsgeometrical alternative: cosine similarity

calculation over the n features

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 55: Case-based Recommender Systems for Personalized Finance Advisory

case-based RSsgeometrical alternative: cosine similarity

calculation over the n features

= (risk profile, experience, goals, etc.)

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 56: Case-based Recommender Systems for Personalized Finance Advisory

case-based RSsgeometrical alternative: cosine similarity

inner product

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 57: Case-based Recommender Systems for Personalized Finance Advisory

case-based RSsgeometrical alternative: cosine similarity

it returns the cosine of the angle between A and B

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 58: Case-based Recommender Systems for Personalized Finance Advisory

case-based RSsgeometrical alternative: cosine similarity

case_A

case_B

cosine

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 59: Case-based Recommender Systems for Personalized Finance Advisory

scenario

case base

step 2

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 60: Case-based Recommender Systems for Personalized Finance Advisory

scenariostep 2

0.3

0.7

0.9

0.1

similarity score

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 61: Case-based Recommender Systems for Personalized Finance Advisory

scenariostep 2

0.3

0.7

0.9

0.1

neighborhood(helpful cases)

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 62: Case-based Recommender Systems for Personalized Finance Advisory

step 3 extraction of candidate portfolios

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 63: Case-based Recommender Systems for Personalized Finance Advisory

scenario

Euro Bonds 30%High Yield Bonds 15%Fixed Rate Bonds 15%

Europe Stocks 20%Emerging Markets Stocks 12%

Money Market 8%

Euro Bonds 30%High Yield Bonds 10%Fixed Rate Bonds 22%

Europe Stocks 23%Emerging Markets Stocks 7%Flessibili Bassa Volatilità 8%

step 2

solutions proposed to the neighbors are labeled as candidate solutions

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 64: Case-based Recommender Systems for Personalized Finance Advisory

step 4 ranking of candidate portfolios

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 65: Case-based Recommender Systems for Personalized Finance Advisory

in real-world scenarios, the case base

contains many helpful cases

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 66: Case-based Recommender Systems for Personalized Finance Advisory

in real-world scenarios, the case base

contains many helpful cases

it is necessary to introduce strategies to filter and rank the cases

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 67: Case-based Recommender Systems for Personalized Finance Advisory

revise

We implemented several ranking strategies

• Temporal ranking

• Clustering

• Diversification

• Financial Confidence Value (FCV)

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 68: Case-based Recommender Systems for Personalized Finance Advisory

revisetemporal ranking

solutions are ranked from the newest to the oldest (or viceversa)

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 69: Case-based Recommender Systems for Personalized Finance Advisory

Euro Bonds 30%

High Yield Bonds 15%

Fixed Rate Bonds 15%

Europe Stocks 20%

Emerging Markets Stocks 12%

Money Market 8%

Euro Bonds 30%

High Yield Bonds 10%

Fixed Rate Bonds 22%

Europe Stocks 23%

Emerging Markets Stocks 7%

Money Market 8%

Euro Bonds 15%

High Yield Bonds 25%

Fixed Rate Bonds 10%

Europe Stocks 40%

Emerging Markets Stocks 2%

Money Market 8%

Euro Bonds 20%

High Yield Bonds 20%

Fixed Rate Bonds 12%

Europe Stocks 35%

Emerging Markets Stocks 5%

Money Market 8%

revisetemporal ranking

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 70: Case-based Recommender Systems for Personalized Finance Advisory

Euro Bonds 30%

High Yield Bonds 15%

Fixed Rate Bonds 15%

Europe Stocks 20%

Emerging Markets Stocks 12%

Money Market 8%

olderolder

Euro Bonds 30%

High Yield Bonds 10%

Fixed Rate Bonds 22%

Europe Stocks 23%

Emerging Markets Stocks 7%

Money Market 8%

Euro Bonds 15%

High Yield Bonds 25%

Fixed Rate Bonds 10%

Europe Stocks 40%

Emerging Markets Stocks 2%

Money Market 8%

Euro Bonds 20%

High Yield Bonds 20%

Fixed Rate Bonds 12%

Europe Stocks 35%

Emerging Markets Stocks 5%

Money Market 8%

revisetemporal ranking

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 71: Case-based Recommender Systems for Personalized Finance Advisory

clustering

solutions are clustered and just a small set of centroids is proposed

revise

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 72: Case-based Recommender Systems for Personalized Finance Advisory

clusteringrevise

Euro Bonds 30%

High Yield Bonds 15%

Fixed Rate Bonds 15%

Europe Stocks 20%

Emerging Markets Stocks 12%

Money Market 8%

Euro Bonds 30%

High Yield Bonds 10%

Fixed Rate Bonds 22%

Europe Stocks 23%

Emerging Markets Stocks 7%

Money Market 8%

Euro Bonds 15%

High Yield Bonds 25%

Fixed Rate Bonds 10%

Europe Stocks 40%

Emerging Markets Stocks 2%

Money Market 8%

Euro Bonds 20%

High Yield Bonds 20%

Fixed Rate Bonds 12%

Europe Stocks 35%

Emerging Markets Stocks 5%

Money Market 8%

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 73: Case-based Recommender Systems for Personalized Finance Advisory

clusteringcluster 1

reviseEuro Bonds 30%

High Yield Bonds 15%

Fixed Rate Bonds 15%

Europe Stocks 20%

Emerging Markets Stocks 12%

Money Market 8%

Euro Bonds 30%

High Yield Bonds 10%

Fixed Rate Bonds 22%

Europe Stocks 23%

Emerging Markets Stocks 7%

Money Market 8%

Euro Bonds 15%

High Yield Bonds 25%

Fixed Rate Bonds 10%

Europe Stocks 40%

Emerging Markets Stocks 2%

Money Market 8%

Euro Bonds 20%

High Yield Bonds 20%

Fixed Rate Bonds 12%

Europe Stocks 35%

Emerging Markets Stocks 5%

Money Market 8%

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 74: Case-based Recommender Systems for Personalized Finance Advisory

clusteringcluster 1 cluster 2

reviseEuro Bonds 30%

High Yield Bonds 15%

Fixed Rate Bonds 15%

Europe Stocks 20%

Emerging Markets Stocks 12%

Money Market 8%

Euro Bonds 30%

High Yield Bonds 10%

Fixed Rate Bonds 22%

Europe Stocks 23%

Emerging Markets Stocks 7%

Money Market 8%

Euro Bonds 15%

High Yield Bonds 25%

Fixed Rate Bonds 10%

Europe Stocks 40%

Emerging Markets Stocks 2%

Money Market 8%

Euro Bonds 20%

High Yield Bonds 20%

Fixed Rate Bonds 12%

Europe Stocks 35%

Emerging Markets Stocks 5%

Money Market 8%

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 75: Case-based Recommender Systems for Personalized Finance Advisory

insight: filtering out too similar solutions

diversification algorithmrevise

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 76: Case-based Recommender Systems for Personalized Finance Advisory

revise

identification of the best subset of similar cases which maximize the relative diversity

diversification algorithm

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 77: Case-based Recommender Systems for Personalized Finance Advisory

revisediversification algorithm

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 78: Case-based Recommender Systems for Personalized Finance Advisory

revise

input similar cases

(candidate solutions)

diversification algorithm

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 79: Case-based Recommender Systems for Personalized Finance Advisory

revise

output subset of

diversified cases

diversification algorithm

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 80: Case-based Recommender Systems for Personalized Finance Advisory

revise

algorithm in each step the portfolio which best diversifies the solutions is

chosen

diversification algorithm

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 81: Case-based Recommender Systems for Personalized Finance Advisory

revise

Solutions with the highest quality are iteratively

chosen

diversification algorithm

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 82: Case-based Recommender Systems for Personalized Finance Advisory

revise

combination between

similarity and diversity

diversification algorithm

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 83: Case-based Recommender Systems for Personalized Finance Advisory

it returns portfolios that are not so similar to those

previously put in the result set

revisediversification algorithm

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 84: Case-based Recommender Systems for Personalized Finance Advisory

revisediversification algorithm

Euro Bonds 30%

High Yield Bonds 15%

Fixed Rate Bonds 15%

Europe Stocks 20%

Emerging Markets Stocks 12%

Money Market 8%

Euro Bonds 30%

High Yield Bonds 10%

Fixed Rate Bonds 22%

Europe Stocks 23%

Emerging Markets Stocks 7%

Money Market 8%

Euro Bonds 15%

High Yield Bonds 25%

Fixed Rate Bonds 10%

Europe Stocks 40%

Emerging Markets Stocks 2%

Money Market 8%

Euro Bonds 20%

High Yield Bonds 20%

Fixed Rate Bonds 12%

Europe Stocks 35%

Emerging Markets Stocks 5%

Money Market 8%

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 85: Case-based Recommender Systems for Personalized Finance Advisory

revisediversification algorithm

Euro Bonds 30%

High Yield Bonds 15%

Fixed Rate Bonds 15%

Europe Stocks 20%

Emerging Markets Stocks 12%

Money Market 8%

Euro Bonds 30%

High Yield Bonds 10%

Fixed Rate Bonds 22%

Europe Stocks 23%

Emerging Markets Stocks 7%

Money Market 8%

Euro Bonds 15%

High Yield Bonds 25%

Fixed Rate Bonds 10%

Europe Stocks 40%

Emerging Markets Stocks 2%

Money Market 8%

Euro Bonds 20%

High Yield Bonds 20%

Fixed Rate Bonds 12%

Europe Stocks 35%

Emerging Markets Stocks 5%

Money Market 8% XXC.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 86: Case-based Recommender Systems for Personalized Finance Advisory

reviseFinancial Confidence Value (FCV)

• Simple insight

• We know the historical yield for each of the assets class in the portfolio

• FCV ranks first the solutions composed by a combination of asset classes close to the optimal one (according to previous yield)

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 87: Case-based Recommender Systems for Personalized Finance Advisory

revise

(Generated yield) (Drift Factor)Total yield is the product of the

yield generated by each asset

class with the its percentage in the

portfolio

Ratio between the yield

generated by the asset classes in the portfolio and its complement

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Financial Confidence Value (FCV)

Page 88: Case-based Recommender Systems for Personalized Finance Advisory

revise

Euro Bonds - - - 30%

High Yield Bonds 15%

Fixed Rate Bonds 15%

Europe Stocks +++ 20%

Emerging Markets Stocks 12%

Money Market 8%

Euro Bonds - - - 30%

High Yield Bonds 10%

Fixed Rate Bonds 22%

Europe Stocks +++ 23%

Emerging Markets Stocks 7%

Money Market 8%

Euro Bonds - - - 15%

High Yield Bonds 25%

Fixed Rate Bonds 10%

Europe Stocks +++ 40%

Emerging Markets Stocks 2%

Money Market 8%

Euro Bonds - - - 20%

High Yield Bonds 20%

Fixed Rate Bonds 12%

Europe Stocks +++ 35%

Emerging Markets Stocks 5%

Money Market 8%

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Financial Confidence Value (FCV)

Page 89: Case-based Recommender Systems for Personalized Finance Advisory

revise

Euro Bonds - - - 30%

High Yield Bonds 15%

Fixed Rate Bonds 15%

Europe Stocks +++ 20%

Emerging Markets Stocks 12%

Money Market 8%

Euro Bonds - - - 30%

High Yield Bonds 10%

Fixed Rate Bonds 22%

Europe Stocks +++ 23%

Emerging Markets Stocks 7%

Money Market 8%

Euro Bonds - - - 15%

High Yield Bonds 25%

Fixed Rate Bonds 10%

Europe Stocks +++ 40%

Emerging Markets Stocks 2%

Money Market 8%

Euro Bonds - - - 20%

High Yield Bonds 20%

Fixed Rate Bonds 12%

Europe Stocks +++ 35%

Emerging Markets Stocks 5%

Money Market 8%

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Financial Confidence Value (FCV)

Page 90: Case-based Recommender Systems for Personalized Finance Advisory

step 5 discussion of the solution

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 91: Case-based Recommender Systems for Personalized Finance Advisory

financial advisor and private investor

can further discuss the portfolio

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 92: Case-based Recommender Systems for Personalized Finance Advisory

review

Original Discussed Gap

Euro Bonds 30% 30%High Yield Bonds 12.5% 10% -2.5%Fixed Rate Bonds 18.5% 20% +1.5%

Europe Stocks 21.5% 24% +2.5%Emerging Markets

Stocks 9.5% 8% -1.5%Money Market 8% 8%

interactive personalization

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 93: Case-based Recommender Systems for Personalized Finance Advisory

step 6 case base update

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 94: Case-based Recommender Systems for Personalized Finance Advisory

an evaluation score is finally assigned to the proposed solution

yield, e.g.

retain

good solutions are stored in the case base and exploited for future recommendations

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 95: Case-based Recommender Systems for Personalized Finance Advisory

case base

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 96: Case-based Recommender Systems for Personalized Finance Advisory

(new) case base

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 97: Case-based Recommender Systems for Personalized Finance Advisory

our implementation

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 98: Case-based Recommender Systems for Personalized Finance Advisory

our implementationhttp://193.204.187.192:8080/OBWFinance

demo available

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 99: Case-based Recommender Systems for Personalized Finance Advisory

OBWFinancelogin screen

advisor-oriented tool

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 100: Case-based Recommender Systems for Personalized Finance Advisory

OBWFinanceclient selection

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 101: Case-based Recommender Systems for Personalized Finance Advisory

OBWFinancerecommendation parameters

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 102: Case-based Recommender Systems for Personalized Finance Advisory

OBWFinanceonly admins can change the parameters

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 103: Case-based Recommender Systems for Personalized Finance Advisory

OBWFinanceone click to generate recommendations

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 104: Case-based Recommender Systems for Personalized Finance Advisory

OBWFinancedrop-down menu for selecting the best solution

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 105: Case-based Recommender Systems for Personalized Finance Advisory

OBWFinanceassets class

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 106: Case-based Recommender Systems for Personalized Finance Advisory

OBWFinanceyield of the solution

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 107: Case-based Recommender Systems for Personalized Finance Advisory

OBWFinancechosen portfolio can be further discussed

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 108: Case-based Recommender Systems for Personalized Finance Advisory

evaluation

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 109: Case-based Recommender Systems for Personalized Finance Advisory

evaluationwhat is the average yield of

recommended portfolios?

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 110: Case-based Recommender Systems for Personalized Finance Advisory

evaluationwhat is the average yield of

recommended portfolios?

can recommender systems suggest

better investment portfolios than human advisors?

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 111: Case-based Recommender Systems for Personalized Finance Advisory

design of the experiment

• 1172 users

• 19 assets classes

• Different neighborhood sizes

• Different features describing the users

• Risk Profile, Investment Goals, Investment Horizon, Investment Experience, Financial Assets, Advice Type, Sex, Age

• Different similarity measures (Cosine vs. UserMatch)

• Leave-one-out experimental design

evaluation

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 112: Case-based Recommender Systems for Personalized Finance Advisory

experiment 1user match vs. cosine similarity

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Yiel

d

0

0,04

0,08

0,12

0,16

0,2

neighbors

1 5 10

0,20,190,18

0,10,110,09

User Match Cosine Sim

cosine similarity overcomes user match

Page 113: Case-based Recommender Systems for Personalized Finance Advisory

experiment 2how many features?

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Yiel

d

0

0,042

0,084

0,126

0,168

0,21

neighbors

1 5 10

0,20,210,2 0,20,190,18

Financial Features Financial + Demographical Features

cosine similarity overcomes user match

Page 114: Case-based Recommender Systems for Personalized Finance Advisory

experiment 3revise strategies (yield)

best performing configuration provides 0,28% monthly yield

Yiel

d

0

0,056

0,112

0,168

0,224

0,28

neighbors

1 5 10

0,250,240,22

0,270,28

0,220,2

0,150,13 0,14

0,120,09

0,20,210,2

Basic Clustering Diversification FCV FCV + Div

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 115: Case-based Recommender Systems for Personalized Finance Advisory

experiment 3revise strategies (diversity of the solutions)

ILD=1-average similarity between portfolios

Intra

-Lis

t Div

ersi

ty (I

LD)

0

0,14

0,28

0,42

0,56

0,7

neighbors

0,58

0,35

0,7

0,460,41

Basic Clustering Diversification FCV FCV + Div

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 116: Case-based Recommender Systems for Personalized Finance Advisory

experiment 4comparison to baselines (leave-one-out evaluation)

recsys better than humans!

Yiel

d

0

0,056

0,112

0,168

0,224

0,28

neighbors

1 5 10

0,270,28

0,220,20,20,2

0,170,170,17

Human Collaborative FCV

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 117: Case-based Recommender Systems for Personalized Finance Advisory

• FCV calculated on January, 2014

• Recommendations generated on January, 2014

• Evaluation of the yield generated from February 2014 to July 2014

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

experiment 5ex-post evaluation (6 months, with real data)

Page 118: Case-based Recommender Systems for Personalized Finance Advisory

experiment 5ex-post evaluation (6 months, with real data)

FCV and Diversification is the best one

Yiel

d

0

0,032

0,064

0,096

0,128

0,16

neighbors

1 5 10

0,060,060,060,040,04

0,05

0,110,12

0,16

0,090,1

0,16

0,060,08

0,15

Basic FCV FCV + Div Collaborative Human

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 119: Case-based Recommender Systems for Personalized Finance Advisory

• Personalized Wealth Management

• Application of case-based reasoning

• Geometrical similarity measure to identify the most similar previously solved cases

• Introduction of diversification and re-ranking techniques

• More than 3% yield for year

• Experiments shows that recommended portfolios overcome the real ones for almost all the users

• Working Demo!

recap

C.Musto, G.Semeraro - Case-based Recommender Systems for Personalized Finance Advisory FinRec 2015 - 1st International Workshop on Personalization and Recommender Systems in Financial Services - Graz (Austria) - 16.04.2015

Page 120: Case-based Recommender Systems for Personalized Finance Advisory

questions?

Giovanni Semeraro [email protected]

Cataldo Musto [email protected]

in memoriam

Aaron Swartz