A major, UK, consumer finance company, focused on sub-prime, on-line lending. The client was an early, fintech innovator experiencing problems in handling its rate of growth.
The client’s existing systems were constructed using mainly traditional banking components, e.g. decision engine, range of credit/default scorecards, loan management system, CRM and general ledger system etc. The client was collecting a limited range of predictive data.
Whilst the client was using well proven banking modules, in the context of on-line lending they lacked functionality and imposed a number of restrictions. The main issues were,
• Insufficient data capture in front-end processes to support accurate and granular predictions for defaults, fraud, retention, and limitsAs a result, portfolio performance was sub-optimal and operating costs per loan were high. Plus, whilst market response was good, the system was unable to cost effectively cope with portfolio growth.
The subprime lending portfolio base KPIs required improvement. Zoral DE and Zoral ML were used to rapidly construct a parallel decisioning system to baseline the client’s current KPI’s. These were,
• Average loan size - £260.00
• Number of online applications processed daily - 70
• % of manual processing - 76%
• Operating costs per new loan - £8.30
• Operating costs to provide repeat loan for an existing customer - £2.50
• New customer acquisition costs averaged - £42.00
• Fully loaded, semi-automated retention marketing costs per loan - £2.20
• Portfolio default rate was very high - 28%
• Acceptance rate could not be accurately calculated due to data quality issues, estimated at 19%
• Customer retention rate - 51%
• Fraud rate - 6%
After the baseline KPIs were calculated, an enhanced customer journey was constructed using Zoral DJ, Zoral BDW and Zoral DE intelligent workflows. This captured additional, predictive data and significantly improved data collection and quality. A further range of additional predictive data was captured over a two month period. This included behavioral, social, device, and bureau data.
Zoral ML default, fraud, retention, limit management models were tuned on an enhanced range of predictive portfolio data. This was done using Zoral ADW, advanced feature engineering techniques, and robo-underwriter. The following were automated, using Zoral DE intelligent workflows, and Zoral ML:
• KYC verifications
• Fraud detection / prevention and underwriting
• Retention prediction and management
After three months, the client’s subprime lending portfolio KPIs improved as follows,
• Average loan size increased to £310.00The client’s profitability and scalability rapidly improved. However further optimization was required for new customer acquisition costs, defaults, limit management, acceptance rates.
Plus manual processing needed to be further reduced.
Zoral ML models and workflows were further tuned after four months’ data collection and a number of A/B testing initiatives. A number of additional models and intelligent workflows were introduced, including,
• Zoral ML lead evaluation
• Targeted marketing
• Conversion
• Collection optimization
• Data cost optimization models
These supported automated, optimized customer lifecycle management.
• Customer acquisition across a number of digital channels, including social, search, and through integration with a number of UK lead generators| KPI | Prior to using Zoral platform tools | After 5 months | After 12 months |
|---|---|---|---|
| Average loan size | £260.00 | £310.00 | £540.00 |
| Number of online / mobile applications processed & approved per day | 70 | 500 | 10K+ per day (subsequently peaked at over 100K per day worldwide) |
| % of manual processing | 76% | 15% | < 2% (some manual intervention retained due to regulatory requirements) |
| Operating costs per new loan | £8.30 | £2.80 | £1.30 (primarily data acquisition costs) |
| Operating costs to provide another loan for an existing customer | £2.50 | £0.60 | £0.40 |
| New customer average acquisition cost | £42 (non-scalable) | £126 (scalable, but expensive) | < 12% of loan face amount, across all digital channels |
| Retention marketing cost for each portfolio customer identified for retention | £2.20 | £0.34 | £0.21 |
| Portfolio default rate | 28% | 18% | Sub 8% |
| Acceptance rate new customers | Estimated at 19% | 25% | 29% |
| Customer Retention Rate | 51% | 78% | 87% |
| Fraud rate | 6% | 2% | < 0.1% |
| Summary | Small innovative finance company, sub-optimal KPI’s. Platform not scalable, high operating costs per loan | Implemented Zoral platform robo underwriter and intelligent STP. Increased profitability, significantly improved scalability and core KPI’s | One of the most successful financial (Fintech) startups in Europe. Low operating costs, intelligent robo underwriter, effective digital targeted marketing, optimized customer lifecycle management £400+ mil online revenue |
• 53% increase in acceptances
• 72% reduction in default rate
• 97% reduction in manual effort
• 82% reduction in fraud rate
Ready to lead with innovation? Fill out the form below to connect with one of our expert consultants, and discover how Olympus fOS can help.