Excellence Awards 2016: Mandy Luo - Best Use of Predictive

[JulieH]

Author: Mandy Luo, Chief Actuary and Head of Data Analytics

Company: ReMark International

Awards Category: Best Use of Predictive

As a trained Statistician, I understand why "70% data, 30% model" is not an exaggeration. Therefore, before applying any regression models, I always make sure that input data are fully reviewed and understood. I use various data preparation tools to explore, filter, select, sample or join up data sources. I also utilize the data investigation tools to conduct or validate any statistical evaluation. Next, I would usually choose 3-5 predictive modeling candidates depending on the modeling objective and data size. I often include one machine learning methods in order to at least benchmark other models. After the modeling candidates finish running, I would select the best model based on both art (whether the coefficients look reasonable based on my understanding of the data and business) and science (statistical criteria's like the goodness of fit, P-value and cumulative lift etc.).  I am also often using the render function for model presentation and scoring/sorting  function for model validation and application.

Describe the problem you needed to solve 

ReMark is not only an early adopter in predictive modeling for life insurance, but also a true action taker on customer centricity by focusing on customer lifetime analytics (instead of focusing on 'buying' only). In this context, we need to 'join up' our predictive models on customer response, conversion and lapse in order to understand the most powerful predictors that drive customer activities across pre and post sales cycle. We believe the industry understand that it is insufficient to only focus on any single customer activity, but is still exploring how this can be improved through modeling and analytics, which is where we can add value.

Describe the working solution

Our working solution goes with the following steps:

1. Match over one year post sales tracking data back to sales payment data and marketing data (all de-personalized)
2. Build 3 predictive models: sale(whether the purchase is agreed or not), conversion (whether the first premium bill is paid or not), 1 year persistency (whether lapse happened at month 13 or not).
3. Compare model results by key customer segments and profiles
4. Expert to visualization tool (e.g. Tableau) to present results
5. Model use test: scoring overlay and optimization strategy

Describe the benefits you have achieved

• We could create customer segments' not just based on tendency to 'buy', but also tendency to 'pay' and 'stay'.
• We could further demonstrate ReMark's analytics and modeling capabilities covering the whole customer lifetime value chain without missing out