Approach - Actionable Analytics

In this blog post, we will discuss on the approach we can follow to provide an actionable analytics. Doing actionable analytics is not easier said than done. It requires a focused analytical process. Here we will outline the three important phase or levers that can improve the process of delivering actionable analytics. The three phases can help you to improve the financial aspects of the business by doing actionable analytics.

• Discover
• Explore 
• Engage

For example, if we are delivering actionable analytics for the marketing function. In each phase we will identify some critical characteristics or parameters that are going to influence the financial value directly or indirectly.

Discover - Customer Segmentation, Classification and Marketing Channel.

Explore - Cross Sell, Up Sell, Reduce number of profitable customers.

Engage - Customer Value Management, Life Time Value, Retention and Profitability.

In the Discover phase, the goal is to be able to identify the customer segments that have high engagement with the business and the marketing channels that are driving the most highly engaged customers to the business. Customer segmentation is more critical to gain knowledge about the customer segments. Higher the time spent in the discovery phase to identify the customer segments higher the effectiveness of the results in the next phase.

In the Explore phase, the goal is to make use of the knowledge that we have gained about the customer segments and marketing channel. We will make use of the knowledge to further amplify the monetary value by exploring the options such as cross sell and up sell opportunities. In the explore phase we have got to make sure that we approach cross sell and up sell opportunities to the customers who are more likely to respond to the campaigns.

In the Engage phase, this is the most critical phase as most of the strategic level analysis shall be done to engage with the customers to maintain the profitability for the business. This is the phase where most advanced level of modelling process is required.

“Customer value management (CVM) is a process that refines and leverages the benefits of customer relationship management. It encompasses customer identification, contact management, campaign management, advanced data modeling and customer scoring” Customer Value management shall be the high level strategic objective for any business to focus on.

The first phase is more of descriptive in nature and the other two phases are highly inferential in nature where advanced and predictive modelling techniques are applied to derive knowledge.
The above mentioned three phases are relative to each other to provide actionable analytics. Context and relevance are two important parameters one should remember while doing the analysis on each phase. Analyst must be able to interlink between all three phase so that results are inevitable. If each phase is executed in a meticulous manner, the results will be highly significant.

BANKING BUSINESS AND BANKING INSTRUMENTS-2

In the last blog we had discussed three types of banking instruments, namely the Current account, Savings account and Certificate of Deposit.  In this blog we discuss credit cards. Credit cards are the most expensive and profitable type of loan that a bank can extend. A credit card is a card issued by a financial institution giving the holder an option to borrow funds, usually at points of scales. Credit cards charge interest and are primarily used for short-term financing. Interest usually begins one month after a purchase is made and borrowing limit is pre-set according to the individual’s credit rating. Credit cards have higher interest rates than most consumer loans, or lines of credit.

Why credit cards are called ‘Revolving lines of credit’?

Credit cards are called Revolving lines of credit since it is a line of credit where the customer pays a commitment amount and is then allowed to use the funds when they are needed. It is usually used for operating purposes, fluctuating each month depending on the customers current cash flow needs.  The lending institution grants a maximum credit limit which can be used to make purchases at any time and on any goods. The credit line can be used repeatedly as long as the maximum is not exceeded. Since, the credit goes in and out of the account it is ‘revolving’ in nature.




Credit Card Lifecycle:

There are five stakeholders to the credit card lifecycle: (a) Cardholder (b) Retailer/merchant (c) Acquirer (d) card scheme (e) Issuer.

(a) Cardholder: This is a person holding a debit, credit or charge card issued by a financial institution.
(b) Retailer/Merchant: A merchant who sells the goods or services to the customers.
(c) Acquirer: A merchant will have negotiated a merchant service agreement with its acquirer to process payment card transactions details from the merchant’s terminal passing these through the card issuer via the card scheme for authorisation and completion of the process.
(d) Card Schemes: Card Schemes are organisations that manage and control the operation and clearance of card payment transactions, according to card scheme rules.
(e) Issuer: The issue is the bank, building society or financial organisation that provides payment cards.

Analytics of Credit Cards:

Analytical Modelling is required at different points of the credit card business line. There are four distinct phases of a consumer’s credit life cycle for credit cards and other aligned lines of business (such as loans.): (i) Business Verification/ Fraud verification (ii) Decision Making (iii) Account/Portfolio management (iv) Collections.

(i) Business Verification: This is the initial phase and comprises of confirming a prospective customer. This process involves validating the history of the customer, or the company who approaches the bank for loans. The borrower’s credit history, with the lending bank as well as with other banks is important to understand for the lenders. The total number of consumers walking up to the bank for credit cards (or any such loans) is called the Through The Door population. The bank uses data from credit bureaus to develop origination scorecards to segregate the good customers from bad customers. The technique used extensively is Logistic Regression.

(ii) Decision Making: The need to make decision arises at any point in time of the credit life cycle. The credit managers are helped by “triggers” which help them to understand the changing nature of the customer profiles. These triggers add more predictive capacity to the models, by adding more dynamic information from time to time. Techniques applied here are cut-off analysis, watch list modelling.

(iii) Account/Portfolio Management: This acts as a pre-emptive strategy to mitigate loss. Because customer situations can change rapidly, a portfolio management data system must be such that it can be used to easily assess current information on a customer’s payment history.  PD, LGD and EAD models are developed to monitor the performance of the obligors on books. The statistical techniques used are Logistic Regression, Linear Regression.

(iv) Collections: Collections is the phase that managers wish they never reach. To ensure that proper collections are done, getting the proper contacts of the customers is absolute necessity. A commercial skip-tracing tool to uncover alternative information and to identify and to identify any other addresses than the one provided for, are suggested to build reliable commercial databases.

In the next blog we will discuss Mortgages and the relevant analytical models for them.