retail energy analytics_marketelligent
Post on 11-Aug-2014
63 Views
Preview:
DESCRIPTION
TRANSCRIPT
Application of Decision Sciences
to Solve Business Problems
For Retail Energy Provider’s (REP’s)
Demand Planning
Forecasting
In the domain of energy, there is a need to respond to shifting production constraints and changing demandson a regular basis. In order to determine how best to buy electricity in the market, any REP must accuratelypredict and forecast future demands, so that they can plan supply accordingly. Energy trading & hedging isone of the most crucial activities for ensuring reliable electricity supply and achieving economy. Forecasting isa pre-requisite for hedging.
Forecasts models are built by taking into account historical power consumption patterns, production costs,operational constraints and regulations, peak selling times, value of carbon credits, weather forecasts(forecasts of temperature, wind, rain & humidity), grid transmission capacity amongst other factors. Thesemodels use the data to project demand in the near future for different geographical locations.
Development Validation Forecast
Ener
gy (
MM
kW
hr)
Predicted Development Predicted Validation Forecast
0
2
4
6
8
10
12
14
16
18
20
Jan-11 Feb-11 Mar-11 Apr-11 May-11 Jun-11 Jul-11 Aug-11 Sep-11 Oct-11 Nov-11 Dec-11 Jan-12 Feb-12 Mar-12 Apr-12 May-12 Jun-12 Jul-12 Aug-12 Sep-12 Oct-12 Nov-12 Dec-12
Customer Acquisition
0%
5%
10%
15%
20%
25%
1 2 3 4 5 6 7 8 9 10
Hot Leads Warm Leads
Random; 10.9% leads
Predictive Model
% L
ead
s
Predictive Model Deciles; Each decile has 10 % of Leads
Cold Leads
Response models to target the right prospects and optimize acquisition budgets
Prospect Targeting
Earlier, REP’s used to function in a regulated, non-competitive environment where marketing consistedprimarily of brand awareness and public relations efforts. However, these days, deregulation allows customersto choose their suppliers. Also, pricing pressure, thin margins, energy efficiency, load management, renewableenergy, frequent M&A activity, etc add to the complexity and competition, and hence acquiring newcustomers has become a challenge.
Prospect acquisition is specifically concerned with issues like acquiring the right prospect at an optimal cost,acquiring as many prospects as possible, optimizing across channels, etc. The main objectives are ensuringhigh profitability of new customers and acquiring them at a low cost. By analyzing prospect demographics,predictive modeling techniques are employed to identify their propensity to respond. Profitability models arethen built for different segments. It helps in answering business questions like: How do we proactively acquire new customers? Who will be the most profitable customers? And in which channels do we target them? Can the varied data sources be leveraged to expand prospect universe and implement efficient direct
marketing campaigns? How can direct marketing spends be lowered while maintaining results?
Loyalty Analytics
Tenure<12mo
All Customers1,889
1,637 MM USD87k USD/Customer
New Customers4,568 (24%)
433 MM USD (27%)95k USD/Customer
Existing Customers11,573 (76%)
1,203 MM USD (73%)84k USD/Customer
Savers2,944 (16%)
39 MM USD (2%)13k USD/Customer
Heavy Users7,316 (38%)
812 MM USD (50%)111k USD/Customer
Switchers871 (5%)
60 MM USD (4%)69k USD/Customer
Seasonal3,190 (17%)
292 MM USD (18%)92k USD/Customer
Customer Segmentation
Energy providers are transition from supply to demand, from production to marketing. To manage the shiftfrom being cost centers to revenue opportunities, it is important to understanding the customer base better.
Segmentation is the practice of identifying homogenous groups of customers based on their needs, attitudes,usage & consumption behavior. It enables identifying profitable customer segments and customizing productand service offerings and marketing campaigns to target them effectively. It is typically done using acombination of transaction data, demographic data, psychographic information, location and premiseattributes. Besides increasing conversion rates, targeted strategy helps drive energy efficiency and peak loadreduction to optimize the economic return on smart grid & smart meter investment programs. It aids inanswering critical business questions like: How can energy providers cut costs & focus resources & investments on secondary products? How can they connect the right offers to the right customer segments and respond to the needs in
electricity generation & transmission value chain? How do they comply with regulatory guidelines for energy efficiency based on different customer
segments’ energy consumption patterns during peak or off-peak hours? Which customer groups are most likely to enroll for different tariff programs like energy-efficiency and
what are their characteristics? How should contact channels be aligned to communicate with them?
Segmenting customers based on their revenue contribution
Loyalty Analytics
00.5
11.5
22.5
<15 15-25 25-40 40-60 >60
100%
80%
60%
40%
20%
0%
Revenue Break-up by Age-Group Revenue Break-up by Cities
3,327(19%)$12000/Customer
$40MM(12%)
7,750(44%)$5,000/Customer
$39MM(11%)
4,421(25%)$25000/Customer
$111MM(33%)
2,118(12%)$70000/Customer
$148MM(44%)
Incr
easi
ng
CLV
Customer Life Time Value
Wherever markets have been deregulated, utilities are under pressure to maximize their revenues as well ascontrol operating expenses. Higher costs, unforeseen service disruptions and increased customerexpectations have made it essential for utility companies to give importance to high value customers.
Customer lifetime value(CLV) represents how much a customer is worth in monetary terms and is based oncustomer’s expected retention and spending rate. It can be defined as the present value of the total profitexpected from the customers during the entire period they do business with the company. CLV analysis usescustomers’ past transaction data and employs predictive modelling techniques to forecast how much eachcustomer would contribute to the company’s revenues and profits till they remain with the company and donot attrite. CLV analysis takes into account estimated annual profits from customers, duration of businessrelation of the customer, and the discount rate to assess the net present value of the customers. It helps in: Forecasting the expected revenue from new customers and weighing it against the acquisition and
retention cost for them Deciding how much to spend on marketing programs for different customers Identifying the high value customer segments that can contribute the maximum to company’s revenue
and have special offers for them Identify the prospects who can become profitable for the company
0
100
200
300
400
500
Customers : 1,050DNP : 8.2%
Customers :2,127DNP : 2.6%
Customers : 685DNP : 10.4%
Customers : 565DNP : 4.5%
Customers : 616DNP : 9.1%
Customers : 1,511DNP : 1.3%
Customers : 546DNP : 11.0%
Customers : 139DNP : 2.6%
Customers : 393DNP : 11.5%
Customers : 223DNP : 1.6%
Credit Range
550-679 <549, >680, No credit score, Pre-approved
Dwelling typeTDSP
ONC AEPC,AEPN,CNP,TNMP APARTMENT HOUSE, MOBILE
Contract term
Agent, Internal Sales, Telesales6,9,12 months 18,24 months
Sales channel
Online
Total Customers : 2,177DNP : 3.5%
Rules to identify customers having a higher likelihood of disconnecting for non-payment (DNP)
Churn Management
Due to de-regulation and increasing competition in the energy utilities market, customer attrition is on therise for lower bills, better tariff plans or better customer service. To retain them, it is very essential to keeptracking customers’ activity regularly — their frequency of consumption, evolution of their usage patterns,how often do they consume and so on. Customers attrite on a definite path to inactivity which can beidentified and therefore managed. Also, acquiring new customers has become expensive and hence retentionhas become a major priority. By employing attrition analysis, customers whose engagement levels havelowered and who are likely to attrite can be identified and usage patterns can be monitored separately.
Churn analysis helps answer key business questions like: Which are the customer segments, with a high likelihood of attrition, with a bad debt How do we identify the factors which are most likely to drive customers to stay Which are the most effective retention programs - constant tracking & monitoring of retention offers
helps gauge the efficacy of program
Loyalty Analytics
Campaign Management
-1000
-500
0
500
1000
1500
2000
$ P
rofi
ts/C
amp
aign $ 2,000
$1,500
$1,000
$500
$0
-$500
-$1000Profitability Segment
High Low
Customer Segments unprofitable and removed from telemarketing
Campaign Effectiveness
Campaigns include a variety of short term programs directed at consumers to stimulate product awareness,trial or purchase. The most commonly implemented programs include special pricing, promotional contests,telemarketing campaigns, reward programs and so on. For utilities, campaigns can be directed at residential orsmall commercial customers or institutions. Competitive retail electricity firms often use direct sales (includingtelephone, door-to-door canvassing, mails, online) to acquire customers. Predictive modeling techniques onpast promotion data can help refine the promotion strategy by understanding lift of various campaigns, theirROI and targeting only the customers with the propensity to buy.
This information is then used by marketers to: Identify the impact of different campaigns and find out the most effective one Optimally allocate budget among different campaigns while increasing sales & maximizing ROI Measure the campaign effectiveness for continuous improvement Targeting only those customers who have a higher propensity to convert
Product Design
Product Design
Retail energy marketers use value-added services to improve customer service and generate incrementalrevenue. Due to de-regulation and increasing competition, bundling of products & services has become apoint of differentiation for retail energy providers. Some REPs offer air conditioning maintenance, smart hometechnologies like smart thermostats, solar panels, home security systems or customized information on theirenergy consumption as part of service bundling. However, it is important to gauge consumer perceptionregarding different services. It is essential for—a) Creating the right product plans based on usage patternsb)Identifying the right value added services
Conjoint analysis techniques are employed on survey data to evaluate how much consumers weigh eachcomponent of the tariff plan and the add on service component in their purchase decision process. It helps insegmenting consumers as per their preferences. This then helps the energy provider in designing the rightplans and value added services and selling it to the right set of customers.
0%
5%
10%
15%
Superlock 12 Fixed 24 Rate Protect12
Safe Rate 12 CertifiedFixed 12
SimplicityOnline 12
StandardMonth to
Month
Earth SaverOnline 12
Winter 11Special
GuaranteedFixed 12
Power AsYou Go Plus
Renew Cleanand Green
12
True GreenSavings 24
Revenue Contribution by Product Plans
Driving Profitability
0%
2%
9%
12%
6%
4%
11%
18%
22%
13% 13% 13%
7%
14%
9%
15%
14%
4%
11%
13%13%
22%
8%
2%
0%
5%
10%
15%
20%
25%
0-2
99
40
0-4
99
53
0-5
49
58
0-5
99
61
0-6
19
63
0-6
39
65
0-6
59
68
0-6
99
72
0-7
39
76
0-7
79
80
0-8
49
90
0-9
49
Bad Debt DNP Profile
0%
2%
9%
12%
6%
4%
11%
18%
22%
13% 13% 13%
7%
14%
9%
15%
14%
4%
11%
13%13%
22%
8%
2%
0%
5%
10%
15%
20%
25%
0-2
99
40
0-4
99
53
0-5
49
58
0-5
99
61
0-6
19
63
0-6
39
65
0-6
59
68
0-6
99
72
0-7
39
76
0-7
79
80
0-8
49
90
0-9
49
% of Disconneted
Credit score range 600-649 for Apartment owners accounts for a high disconnect rate & bad debt
Optimizing Deposit Rules
For availing of electricity supply and consumption, residential and institutional consumers are usually requiredto make deposits with the Retail Energy Providers. It serves as a security in case the customer enters intoarrears and turns to be a bad debt for the company. However, these deposits might differ for differentcustomers based on their credit history and demographic profile. Defining deposit rules by customer profile isvery essential to curb bad debt and losses for energy providers. Deposit rules for different customers aredefined as a function of many elements like credit score, dwelling type, product plan, tariff plan, demographicattributes (age, income, etc.).
Customer profiles are evaluated by analyzing historic disconnect rates, bad debt as a % of revenue/margin,revenue contribution, credit score, service plan, dwelling type and so on. Customer profiles where thedisconnect rate and bad debt are high are segregated from the others. This serves as the basis for defining thedeposit rules of the energy provider for different customers. Optimization algorithms are then built foridentifying the right deposit for each of these rules.
Driving Profitability
Pre-paid customer yielded a negative margin for current year
Decline in revenue compounded by high cost of energy and highbad debt result in this decline
Margin Analysis
Profit margins are expressed as a ratio, specifically “earnings” as a percentage of sales. Margin analysis helpscompanies manage their costs and expenses better and generate higher profits. This involves regular trackingof P&L statements for different customer groups to evaluate profitability movements by analyzing historicdisconnect rates, bad debt as a % of margin, costs and revenue contribution by tariff plans & demographicprofiles (like credit score, age etc.).
It helps in generating a detailed demographic profile of high margin customers vs. low margin customers andanswering business questions like: Do customers with a lower credit score generate greater margin than the bad debt they create? Do customers with extended split deposit option generate more margin than the bad debt they create as
compared to the full deposit customers? Do customers on different tariff plans behave differently vs. other customers in terms of margin?
Business can then accordingly impose the right business rules to reduce risk exposure from these customers.
Driving Profitability
1,560 $439K
Low(<50$) Medium-Low(50-300$) Medium-High(300-500$) High(>500$)
8% 0%
40%21%
37%
30%
15%49%
0%
25%
50%
75%
100%
Bad Debt Consumers Bad Dedt $
49% of the bad debt comes from 15% of the customers
Bad Debt management
Companies in energy domain typically write-off millions each year due to bad debts and there are mainly twochallenges they face—a) Collection efforts start only after a customer enters into arrears b) Mostly a standardapproach is employed for all customers regardless of their demographics. By using predictive analytics in theircustomer strategy, utility companies can get the right message to the right customer at the right time. Loyalcustomers who have consistently paid on time, will be treated different from chronic late payers. Predictiveanalytics can aid the 2 most commonly used approaches.
Pro-active: It helps identify the triggers and events that take place before a customer starts missing payments.Once these triggers are identified, proactive measures are taken to communicate with customers, includingpayment reminders and customized messages.Re-active: It helps to determine who to invest effort in and to prioritize collections activities. Utility companiescan then rank the customers who will most likely pay their debt. This ensures organizations spend time andresources only on the cases that are most likely to have successful outcomes.All of this aids companies in better bad debt management by: Formulating an optimally strategic plan that manages bad debt while maximizing revenues & profitability Segregating regular customers vs. bad debt customers and evaluating:
If there is a typical demographic profile of customers that generate most bad debt If there are any seasonal patterns or any changes in transaction before disconnecting
Vendor Management
2,487 sales1.34 MM$
109$/mo./customer
1235 sales0.93 MM$
112$/mo./customer
1099 sales0.49 MM$
98$/mo./customer
911 sales0.32 MM$
103$/mo./customer
- 23.5 MM kWhr- 1,012 kWhr/mo./cust- 11% clawback- 5% sales drop- 11% DNP- 69% post-paid- 33% pre-paid- 15% early termination*- 5% renewal*- 10% pre-approved- Tenure: 148 days- 7% bad debt- 12% deposit- ---- Avg. credit score: 627
- 4.6 MM kWhr- 1,106 kWhr/mo./cust- 6% clawback- 3% sales drop- 3% DNP- 94% post-paid- 6% pre-paid- 6% early termination*- 1% renewal*- 7% pre-approved- Tenure: 105 days- 6% bad debt- 7% deposit- ---- Avg. credit score: 787
- 8.7 MM kWhr- 1,079 kWhr/mo./cust- 14% clawback- 7% sales drop- 4% DNP- 100% post-paid- 0% pre-paid- 29% early termination*- 10% renewal*- 56% pre-approved- Tenure: 209 days- 6% bad debt- 2% deposit- $196K commission- Avg. credit score: 748
- 2.6 MM kWhr- 911 kWhr/mo./cust- 9% clawback- 4% sales drop- 13% DNP- 97% post-paid- 3% pre-paid- 33% early termination*- 3% renewal*- 0.4% pre-approved- Tenure: 120 days- 30% bad debt- 7% deposit- $98K commission- Avg. credit score: 624
ARDCTelesales
MarketingOnline
AmalgamDoor-to-Door
Telephone RelationsTelesales
Top 4 Vendors account for 71% of the sales, 75% of the revenue
Risk & Reward analysis
The number of vendors and suppliers involved in the generation and transmission of power is large. So is therange of services they provide: relatively low risk transportation to high risk line work, production andtransmission of power, deploying smart metering services, collecting utility payments and managing the creditcollection. Effectively managing vendor and supplier compliance with corporate, legislative and regulatoryrequirements is critical for the efficient and smooth functioning of any utility company.
Constant monitoring and detailed performance evaluation of all vendors is essential to control costs and tosuitably draft the risk & reward policy for each vendor. It includes vendor identification, recruitment,monitoring and quantifying the performance of vendors by evaluating on KPIs (like Pricing, QualitySpecifications and delivery support).
MANAGEMENT TEAMGLOBAL EXPERIENCE.
PROVEN RESULTS.
Roy K. CherianCEORoy has over 20 years of rich experience in marketing, advertising and mediain organizations like Nestle India, United Breweries, FCB and FeedbackVentures. He holds an MBA from IIM Ahmedabad.
Anunay Gupta, PhDCOO & Head of AnalyticsAnunay has over 15 years of experience, with a significant portion focusedon Analytics in Consumer Finance. In his last assignment at Citigroup, he wasresponsible for all Decision Management functions for the US Cardsportfolio of Citigroup, covering approx $150B in assets. Anunay holds anMBA in Finance from NYU Stern School of Business.
Greg FerdinandEVP, Business DevelopmentGreg has over 20 years of experience in global marketing, strategic planning,business development and analytics at Dell, Capital One and AT&T. He hassuccessfully developed and embedded analytic-driven programs into avariety of go-to-market, customer and operational functions. Greg holds anMBA from NYU Stern School of Business
Kakul PaulBusiness Head, CPG & RetailKakul has over 8 years of experience within the CPG industry. She waspreviously part of the Analytics practice as WNS, leading analytic initiativesfor top Fortune 50 clients globally. She has extensive experience in whatdrives Consumer purchase behavior, market mix modeling, pricing &promotion analytics, etc. Kakul has an MBA from IIM Ahmedabad.
ADVANCED ANALYTICAL SOLUTIONS
MARKETELLIGENT, INC.80 Broad Street, 5th Floor, New York, NY 10004
1.212.837.7827 (o) 1.208.439.5551 (fax) info@marketelligent.com
CONTACT www.marketelligent.com
Industry Business Focus Tools and Techniques
Consumer Finance Investment Optimization SAS, SPSS, R, VBA
Credit Cards Revenue Maximization Cluster analysis
Loans and Mortgages Cost and Process Efficiencies Factor analysis
Retail Banking & Insurance Forecasting Structural Equation Modeling
Wealth Management Predictive Modeling Conjoint analysis
Consumer Goods and Retail Risk Management Perceptual maps
CPG & Retail Pricing Optimization Neural Networks
Consumer Durables Customer Segmentation Chaid / CART
Manufacturing and Supply Chain Drivers Analysis Genetic Algorithms
High Tech OEM’s Supply Chain Management Support Vector Machines
Automotive Sentiment Analysis
Logistics & Distribution
YOUR PARTNER FOR
DATA ANALYTICS SERVICES
top related