Client acquisition in financial services can be extremely expensive. Our client needed to identify which customers were most likely to have high client lifetimes as early as possible in their customer journey. Sales and marketing resources could then be focused on those customers who were most likely to prove most profitable.
We conducted a “Data Health Assessment” across the client’s customer journey to understand how client profiles and behaviour was being tracked, identify any gaps or data quality issues. We stitched everything together into a data lake. Applying a range of predictive and machine learning models we rapidly prototyped a system that could predict key events on the customer journey.
Our models enabled our client to efficiently predict how likely a new lead is to convert, their propensity to become a high-value client and anticipated values for lifetime KPIs. These predictions have enabled them to efficiently target their sales, nurturing and retention activities resulting in a significant uplift in revenue and profitability.