ENVISION System

Knowledge Envision
Case Study 1
Case Study 2
Case Study 3

Example 1: Random Forest Prediction

A random forest model is an ensemble model that has a collection of classification and regression trees (CARTs) using random inputs. For each CART, a bootstrap sample of the data is used to train the model. The bootstrap sample is created randomly with replacement from the dataset. With these trained trees, the final result is based on the majority vote of these trees.

ReservePrism Predictive Modeling

 

 

 Please see detail example in our paper

 Predictive Modeling Using Telematics

Example 2: Neural Network

The company wants to predict the final purchases based on customers' quoting history, demographic information and other policy related information. The goal is to provide the recommendation of the most probable final purchases to shorten the sale process and increase the chance of completing the sale.

ReservePrism Predictive Modeling

 

 

Past quotes are available for us to predict the final purchase. The probability of the final purchase changing from the last quote is predicted using the Neural Network model with 5 nodes in the hidden layer, as is illustrated in the diagram to the left.

Example 3: Classification and Regression Tree (CART)

Note: This section and example are from: https://en.wikipedia.org/wiki/Decision_tree_learning

Decision tree learning is a method commonly used in data mining. The goal is to create a model that predicts the value of a target variable based on several input variables. Each leaf represents a value of the target variable given the values of the input variables represented by the path from the root to the leaf.

ReservePrism Predictive Modeling

 

The tree to the left shows survival of passengers on the Titanic ("sibsp" is the number of spouses or siblings aboard). The figures under the leaves show the probability of survival and the percentage of observations in the leaf.

 

Decision trees used in data mining are of two main types:

 Classification tree analysis is when the predicted outcome is the class to which the data belongs.

 Regression tree analysis is when the predicted outcome can be considered a real number (e.g. the price of a house).

ReservePrism Comprehensive Solution