Portfolio
Segmenation

A way of partitioning heterogeneous portfolio in a number of homogeneous segments, in response to differing preferences and past behavior then designing and implementing strategies to target them.

• Have similar profiles and preferences – the whole point of the segment is that you can target groups of similar people who are likely to respond to an appropriate marketing message.
• Profile of each segment should be significantly different from others – each group must have something which separates it from the others. If groups are too similar effect of targeted messaging will be marginal.
• Be large enough to be viable – there is no point in having a highly bespoke segment that includes only a handful of individuals, without having significant size results may not be accurately interpretable. Also having too many segments make strategy development and execution complex.
• Be actionable and targetable – Segment description should be precise, otherwise it will be difficult to be effective. What does it mean to be ‘fun-loving and outgoing’ and how can you target these types of people?
• Suitable product offering – there has to be a product or service that can be effectively sold to this segment so that profitability can be enhanced.

• Socio-economic and geo-demographic segmentation: where people live, their age, culture, household composition, employment, finances and lifestyle.
• Value segmentation: RFM, current value, potential value, lifetime value, margin contribution.
• Behavioural segmentation: deep transactional data, interaction with departments and categories, how customers use products and services, credit risk.
• Attitudinal/needs-based segmentation: core values, needs, reasons customers use products and services; usually identified through market research.
• Preference indicator based segmentation: channels, privacy flags.
• Customer state based segmentation: time-based segments, customer’s position in an event/process/relationship cycle, attrition scores.

• Collate Data – Collation of transaction and demographic data on the account base for the 18 months period.
• Profile the Portfolio – Performing portfolio level analytics to obtain a high level understanding of the portfolio behavior.
• Segment and analyze – Division of portfolio into value based segments. Profiling on demographics, card characteristics and behavioral dimensions.
• Identify opportunities – Based on the segment and portfolio level insights, opportunities are identified and qualified.
• Marketing strategies – Developing of actionable marketing strategies based on opportunities and challenge identified in the analysis.