FINANCIAL SERVICES

Predictive Inactivity Model for a Brokerage Company to Execute Pro-active Retention Campaigns

P R E D I C T I V E
I N A C T I V I T Y
M O D E L T O
E X E C U T E P R O –
A C T I V E
R E T E N T I O N
C A M P A I G N S

T E C H N O L O G Y

ETL – Spark
Data warehouse – MS SQL
Server
Reporting – Power BI
Models – Spark ML,
Regression model,
Predictive model

O B J E C T I V E
Predict which customers are likely to become inactive and to
design appropriate reactivation / retention strategies.

A P P R O A C H
Defined inactivity as customers who did not made any
transaction in the last six months.
Randomly selected 50K customers who had trading accounts
for at least one whole year.
Analyzed customer transactions in the twelve month period
prior to last six months.
Scored customers on 50+ metrics on their equity
transactions – activity, volume, spend, demographics.
Built a regression model using 11 key metrics to predict the
propensity of customers to become inactive.

O U T C O M E
Used model scores to target customers with a high
propensity of inactivity.
A/B testing showed marked improvement in retention of
customers in test groups (based on high model score)
compared to random control groups.