Transcript
Page 1: Financial Recommender Systems

Recommender Systems di prodotti bancari-finanziari

Giovanni Semeraro , Cataldo Musto

Smart Companies and Artificial IntelligenceFirenze (Italy) - May 14, 2013

Page 2: Financial Recommender Systems

outline

• Background

• Needs Allocation

• Anima SGR’s Progettometro

• From Needs to Asset Allocation: recommender systems

• State of the art: Collaborative filtering, content-based filtering

• Our choice: case-based reasoning

• A possible use case

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 3: Financial Recommender Systems

Background

ObjectWay Finance-as-a-ServiceSmart Application Software & Services for Financial

Services Operators

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 4: Financial Recommender Systems

Background

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 5: Financial Recommender Systems

Background

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 6: Financial Recommender Systems

BackgroundWealth Management reference framework

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 7: Financial Recommender Systems

Current work

• Progettometro

• iPad app (https://itunes.apple.com/it/app/progettometro/id515222798?mt=8)

• iOs 4.3 required

• Designed by Anima SGR

• Helps people building their life projects

• Tool for needs allocation

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 8: Financial Recommender Systems

Progettometroprofile selection

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 9: Financial Recommender Systems

Progettometrofive stereotypes

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 10: Financial Recommender Systems

Progettometroinput information

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 11: Financial Recommender Systems

Progettometroprojection

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 12: Financial Recommender Systems

Progettometrolife projects

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 13: Financial Recommender Systems

Progettometroinformation about life projects

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 14: Financial Recommender Systems

Progettometroupdated projection

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 15: Financial Recommender Systems

Progettometrofinal report

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 16: Financial Recommender Systems

from needsto asset allocation

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 17: Financial Recommender Systems

researchquestion

is it possible to evolve a needs allocation tool

towards an asset allocation one by exploiting artificial

inteligence techniques?

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 18: Financial Recommender Systems

our proposal: personalization

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 19: Financial Recommender Systems

to introduce an holistic vision of the user

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 20: Financial Recommender Systems

to adapt asset portfolios on the ground of personal user profile and needs

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 21: Financial Recommender Systems

to introduce a tool helpful for supporting financial advisors (not for private investors!)

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 22: Financial Recommender Systems

SolutionRecommender Systems

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 23: Financial Recommender Systems

Recommender Systems

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

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 24: Financial Recommender Systems

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)

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 25: Financial Recommender Systems

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)

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 26: Financial Recommender Systems

Amazon.com

Testo

“ 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)

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 27: Financial Recommender Systems

Netflix.com

Recommendations

“ 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)

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 28: Financial Recommender Systems

Recommender Systemscurrent literature

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 29: Financial Recommender Systems

Recommender Systemscurrent literature

Collaborative/Social FilteringContent-based Filtering

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 30: Financial Recommender Systems

Recommender Systemscurrent literature

Collaborative/Social FilteringContent-based Filtering

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 31: Financial Recommender Systems

collaborative recommendersSuggest items that similar users liked in the past.

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 32: Financial Recommender Systems

collaborative recommendersSuggest items that similar users liked in the past.

It capitalizes the ‘word of mouth’ effect

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 33: Financial Recommender Systems

collaborative recommendersexample: user-item matrix

item 1 item 2 item 3 item 4

user1 ♥ ♥

user2 ♥ ♥ ♥

user3 ♥

user4

♥ ♥

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 34: Financial Recommender Systems

collaborative recommenderstarget user: user 4

item 1 item 2 item 3 item 4

user1 ♥ ♥

user2 ♥ ♥ ♥

user3

user4

♥ ♥

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 35: Financial Recommender Systems

collaborative recommenderslooking for like-minded users

item 1 item 2 item 3 item 4

user1

♥ ♥

user2 ♥ ♥ ♥

user3 ♥

user4

♥ ♥

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 36: Financial Recommender Systems

collaborative recommendersrecommendationsitem 1 item 2 item 3 item 4

user1

♥ ♥

user2 ♥ ♥ ♥

user3 ♥

user4

♥ ♥

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 37: Financial Recommender Systems

Recommender Systemscurrent literature

Collaborative/Social FilteringContent-based Filtering

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 38: Financial Recommender Systems

content-based recommendersSuggest items similar to those liked in the past by the user

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 39: Financial Recommender Systems

content-based recommenderskey concepts

•Each item has to be described through a set of textual features

•Movie plots, content of news, book summaries, etc.

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 40: Financial Recommender Systems

content-based recommendersexample: news recommendations

Items

User Profile

User is interested in news articles

about sports, football,

cycling, etc.

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 41: Financial Recommender Systems

content-based recommendersexample: news recommendations

Items

Recommendations

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 42: Financial Recommender Systems

content-based recommendersexample: news recommendations

Items

Recommendations

XG.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 43: Financial Recommender Systems

content-based recommendersexample: news recommendations

Items

Recommendations

XG.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013.

Page 44: Financial Recommender Systems

both collaborative and content-based filtering

are not feasible for recommending financial products.

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 45: Financial Recommender Systems

CF drawback: flocking

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 46: Financial Recommender Systems

CF drawback: flocking

Similar users receive similar assets.

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 47: Financial Recommender Systems

CF drawback: flocking

Too many users could be moved towards the same suggestions

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 48: Financial Recommender Systems

CF drawback: flocking

consequence: price manipulation (as in trader forums)

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 49: Financial Recommender Systems

CBRS drawback: poor content

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 50: Financial Recommender Systems

CBRS drawback: poor content

Features describing both assets and private investors are very

poor (e.g. risk profile)

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 51: Financial Recommender Systems

CBRS drawback: poor content

Difficult to calculate the overlap between item and user (feature) description

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 52: Financial Recommender Systems

Solution

Knowledge-based Recommender Systems

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 53: Financial Recommender Systems

Knowledge-based Recommender Systems• Useful for complex domains

• Computers, cameras, financial products

• Need a deep understanding of the domain

• Typically encoded by experts

• Focused on producing correct recommendations

• Focused on explanations of the recommendations

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 54: Financial Recommender Systems

Knowledge-based Recommender Systems• Recommendation process

• Gets information about user needs;

• Exploits the knowledge stored in the KB to meet user needs;

• (eventually) ask user to relax or to modify some of the needs (e.g. expected interest rate);

• Proposes a recommendation.

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 55: Financial Recommender Systems

we focus on a subclass of

knowledge-based recommender systems

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 56: Financial Recommender Systems

we focus on a subclass of

knowledge-based recommender systems

case-based recommender systems

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 57: Financial Recommender Systems

case-based RSs• Knowledge base Case base

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

• To each case is assigned a set of features

• User needs

• Description of the case

• The recommendation process consists of the retrieval and the adaptation of similar already solved cases

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 58: Financial Recommender Systems

case-based RSssolving cycle

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 59: Financial Recommender Systems

case-based RSsformally

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 60: Financial Recommender Systems

case-based RSsformally

item model

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 61: Financial Recommender Systems

case-based RSsformally

item model

= (model, producer, megapixel, zoom, etc.)

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 62: Financial Recommender Systems

case-based RSsformally

item model

= (product, asset class, macro asset class, yield, etc.)

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 63: Financial Recommender Systems

case-based RSsformally

item model

user model

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 64: Financial Recommender Systems

case-based RSsformally

item model

user model

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

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 65: Financial Recommender Systems

case-based RSsformally

item model

user model

session model

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 66: Financial Recommender Systems

case-based RSsformally

item model

user model

session modelevaluation

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 67: Financial Recommender Systems

case-based RSsformally

item model

user model

session modelevaluation

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 68: Financial Recommender Systems

case-based RSsformally

item model

user model

session modelevaluation

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

$ 174.18http://tinyurl.com/d3nt2fq

Page 69: Financial Recommender Systems

given a case base, it is necessary to

define similarity metrics to compute how similar two cases are

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 70: Financial Recommender Systems

case-based RSssimilarity

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 71: Financial Recommender Systems

case-based RSssimilarity

state of the art:heterogeneous euclidean overlap metric

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 72: Financial Recommender Systems

case-based RSssimilarity

n features

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 73: Financial Recommender Systems

case-based RSssimilarity

weight of the i-th feature

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 74: Financial Recommender Systems

case-based RSssimilarity

distance

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 75: Financial Recommender Systems

the retrieved solutions can be refined and modified before being

proposed to the user

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 76: Financial Recommender Systems

solutions considered as ‘correct’ can be stored in the case base and

exploited again in the future

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 77: Financial Recommender Systems

case-based reasoning for financial product recommendation

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 78: Financial Recommender Systems

scenario

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

financial advisor”

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 79: Financial Recommender Systems

step 1user modeling

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 80: Financial Recommender Systems

scenario

Which features may describe

Scrooge McDuck?

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 81: Financial Recommender Systems

scenario

User FeaturesRisk Profile

Financial ExperienceFinancial SituationInvestment GoalsTemporal Goals

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 82: Financial Recommender Systems

scenario

User FeaturesRisk Profile: Low

Financial Experience: HighFinancial Situation: Very HighInvestment Goals: MediumTemporal Goals: Medium

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 83: Financial Recommender Systems

scenario

User FeaturesRisk Profile: Low

Financial Experience: HighFinancial Situation: Very HighInvestment Goals: MediumTemporal Goals: Medium

MiFID-based

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 84: Financial Recommender Systems

in a classical pipeline, the target user would have received a “model” porfolio tailored on her profile

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 85: Financial Recommender Systems

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

similar users.

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 86: Financial Recommender Systems

step 2retrieval of similar users

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 87: Financial Recommender Systems

retrieval

case base

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 88: Financial Recommender Systems

retrieval0.3

0.7

0.9

0.1

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 89: Financial Recommender Systems

retrieval0.3

0.7

0.9

0.1

similarity score

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 90: Financial Recommender Systems

retrieval0.3

0.7

0.9

0.1

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 91: Financial Recommender Systems

retrieval0.3

0.7

0.9

0.1

helpful cases

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 92: Financial Recommender Systems

in real-world scenarios, the case base contains much more helpful cases

usually, it is necessary to introduce some strategy to diversify similar cases

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 93: Financial Recommender Systems

case-based RSsdifferentiate solutions

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 94: Financial Recommender Systems

to each case is assigned an agreed portoflio the set of the portfolios represents the set of the possible recommendations

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 95: Financial Recommender Systems

retrieval

Obbligazionario Euro Bot 30%Obbligazionario High Yield 15%Obbligazionario Globale 15%

Azionario Europa 20%Azionario Paesi Emergenti 12%

Flessibili Bassa Volatilità 8%

Obbligazionario Euro Bot 30%Obbligazionario High Yield 10%Obbligazionario Globale 22%

Azionario Europa 23%Azionario Paesi Emergenti 7%

Flessibili Bassa Volatilità 8%

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 96: Financial Recommender Systems

how to combine the retrieved cases?several strategies available

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 97: Financial Recommender Systems

step 3revise and review

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 98: Financial Recommender Systems

revise and review

Obbligazionario Euro Bot 30%Obbligazionario High Yield 12.5%Obbligazionario Globale 18.5%

Azionario Europa 21.5%Azionario Paesi Emergenti 9.5%

Flessibili Bassa Volatilità 8%

rough average

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 99: Financial Recommender Systems

revise and reviewclustering (proposing diversified solutions)

Obbligazionario Euro Bot 30%

Obbligazionario High Yield 15%

Obbligazionario Globale 15%

Azionario Europa 20%

Azionario Paesi Emergenti 12%

Flessibili Bassa Volatilità 8%

Obbligazionario Euro Bot 30%

Obbligazionario High Yield 10%

Obbligazionario Globale 22%

Azionario Europa 23%

Azionario Paesi Emergenti 7%

Flessibili Bassa Volatilità 8%

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 100: Financial Recommender Systems

financial advisor and private investor can further discuss the portfolio

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 101: Financial Recommender Systems

revise and review

Original Discussed Gap

Obbligazionario Euro Bot 30% 30%

Obbligazionario High Yield 12.5% 10% -2.5%

Obbligazionario Globale 18.5% 20% +1.5%

Azionario Europa 21.5% 24% +2.5%Azionario Paesi

Emergenti 9.5% 8% -1.5%Flessibili Bassa

Volatilità 8% 8%

interactive personalization

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 102: Financial Recommender Systems

an evaluation score is finally assigned to the proposed solution

yield, e.g.

retain

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 103: Financial Recommender Systems

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

retain

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 104: Financial Recommender Systems

case base

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 105: Financial Recommender Systems

(new) case base

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 106: Financial Recommender Systems

recap• Case-based reasoning for recommending financial products

• Goal: to help financial promoters considering solutions proposed to similar users

• Case base: user features and agreed portfolios

• User features: risk profile (MiFID questionnaire), financial experience, financial situation, investment goals, temporal goals

• Portfolio: model portfolio, macro asset classes, asset class distribution, products, etc.

• Similarity: HEOM to retrieve similar ‘cases’

• Revise and Review: several strategies for cases aggregation and combination

• Retain: considering external factors (e.g. yield) to evaluate the effectiveness of the proposed solution

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 107: Financial Recommender Systems

open points• Research is not over :-)

• How to model investors?

• How to model portfolios?

• Which features should be assigned a greater weight?

• Which one is the best strategy to aggregate recommended portfolios?

• How to model temporal constraints?

• How to consider contextual information (e.g., stock market situation) ?

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013

Page 108: Financial Recommender Systems

questions?

Cataldo Musto, Ph.D [email protected]

prof. Giovanni Semeraro [email protected]

G.Semeraro, C.Musto, - Recommender Systems di Prodotti Bancari-Finanziari.Smart Companies and Artificial Intelligence, Firenze (Italy) - May 14, 2013


Top Related