In this challenge, we propose to predict the 5 years Life-Time Value (LTV) of a cohort of Lookiero’s customers.
PROBLEM DESCRIPTION
Life-Time Value (LTV) In marketing, customer life-time value (LTV) is a prognostication of the net profit contributed to the whole future relationship with a customer. The purpose of the customer lifetime value metric is to assess the financial value of each customer. Therefore, LTV is a key metric in every Business To Customer (B2C) business model.
There are different ways to formulate the LTV of a customer. Here, we propose a simple one:
Life-Time Value (time) = Repetition Rate (time) * Average Order Value (time)
The LTV is a time dependent metric, usually described as a time series. The Repetition Rate (RR) is the amount of purchases of a customer in a given time period, and the Average Order Value (AOV) is the average monetary spent of a customer over the purchases up to the given time period.
Usually, the LTV is calculated over a cohort, a group of customers sharing some characteristics, i.e., they ordered for the first time at the same year-month date, they belong to the same market, they belong to the same age group, etc.
OBJECTIVES / EXPECTED OUTCOMES
Lookiero Box
The main Lookiero business channel is Lookiero Box. Given some information from a customer (style, needs, body measurements, etc.), an expert (Personal Shopper) selects five garments that are sent to the customer’ home in a Lookiero Box. The customer tries the garments and then pays for the one that wants to buy and returns the remainers for free.
This is a recurrent, mostly subscription-based business, with an approximately 2-months median frequency and a limited number of items to buy (up to 5).
Lookiero Lookin
Lookiero Lookin is the ultra-personalized Lookiero e-commerce. Our fashion personalization algorithms provide an ultra-personalized e-commerce experience, where each customer can access a selection of garments and looks particularly suited for her style and preferences.
This is an on-demand business model with no limitations to the number of items a customer can purchase at the same time.
REFERENCES
Schmittlein, D. C., D. G. Morrison, R. Colombo. 1987. Counting your customers: Who are they and what will they do next? Management Sci. 33(1) 1–24.
Fader, P. S., B. G. S. Hardie, K. L. Lee. 2005. Counting your customers the easy way: An alternative to the Pareto/NBD model. Marketing Sci. 24(2) 275–284.
Abe, Makoto. 2009. ‘Counting Your Customers One by One: A Hierarchical Bayes Extension to the Pareto/NBD Model. Marketing Sci. 28(3): 541–53.