Decision trees can be used for predictive modelling and machine learning, however, its other capabilities are less acknowledged! Unlike most machine learning techniques, a decision tree is a fully transparent model and as such can be utilised as a surrogate for complex analytical models such as neural networks. Also, the ability to visualise a decision tree makes it an ideal insight tool, especially for capturing complex interactions.
The magic of Weight of Evidence (WoE) transformation. This blog is not a fairy tale, it provides the reality of a robust technique that outperforms many commonly explored techniques. Users are prepared to spend huge amounts of time playing with a handful of techniques but very few can outperform WoE.
Who will win the Rugby World Cup? With input from ex-England rugby player Simon Shaw our data scientists use WPS Analytics to predict the winning team.
High operational cost, fraudulent claims, lengthy claims process with constantly increasing customer demands, and customer dissatisfaction are just few of many challenges of the complex claims management process. The third and final part of our blog series talks about how predictive analytics can make this process more efficient and profitable.
Adequate or fair or competitive insurance quotes? Or even better – adequate, fair and competitive quotes. Challenging but possible. Find out how in the second part of our blog series about insurance.
Why insurance is one of the most challenging business sectors. What are the main issues? How predictive analytics can support the three most important insurance concepts: pricing, claims and fraud detection. Find out in our 3-part blog series about insurance.