Icon

Value Prediction (Logit, Trees, ANN)

GOAL: An insurance company wants to predict the probability that a customer will increase, decrease or not change its value for the company(measured considering both the number and the value of the policies held by the customer).DATA: Dataset containing about 45.000 individual customers of the company, described through 10 variables:VALUE_CHANGE: Change in value (next year) – MULTICLASS TARGET VARIABLEAREA: Region of residenceTENURE: Length of the relationship with the companyAGE: Age of the customerN_ACTIVE_POLICIES: Number of active policiesFLG_HOMEINSURANCE_APP_USAGE: Use of home insurance appAVG_POLICY_DURATION_L4Y: Average policy duration - Last 4 year TOTAL_PREMIUMS_LY: Total Premiums paid (all policies) - Last yearCROSS_SELLING_INDEX: Level of product diffentiation (0= minimum, 100=maximum)PERC_LIFE_POLICIES: Percent of premiums allocated to life policies with hyperparameteroptimizationjoin resultsBalancingwith hyperparameteroptimization Partitioning MLP Logistic Regression Descriptiveanalysis Concatenate Decision Trees Random Forest Analyze results CSV Reader Equal Size Sampling GradientBoosted Trees GOAL: An insurance company wants to predict the probability that a customer will increase, decrease or not change its value for the company(measured considering both the number and the value of the policies held by the customer).DATA: Dataset containing about 45.000 individual customers of the company, described through 10 variables:VALUE_CHANGE: Change in value (next year) – MULTICLASS TARGET VARIABLEAREA: Region of residenceTENURE: Length of the relationship with the companyAGE: Age of the customerN_ACTIVE_POLICIES: Number of active policiesFLG_HOMEINSURANCE_APP_USAGE: Use of home insurance appAVG_POLICY_DURATION_L4Y: Average policy duration - Last 4 year TOTAL_PREMIUMS_LY: Total Premiums paid (all policies) - Last yearCROSS_SELLING_INDEX: Level of product diffentiation (0= minimum, 100=maximum)PERC_LIFE_POLICIES: Percent of premiums allocated to life policies with hyperparameteroptimizationjoin resultsBalancingwith hyperparameteroptimization Partitioning MLP Logistic Regression Descriptiveanalysis Concatenate Decision Trees Random Forest Analyze results CSV Reader Equal Size Sampling GradientBoosted Trees

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: Daniele
Created at: 2020-02-25
On NodePit since: 2023-04-19
Last update: 2024-12-23
Created with KNIME version: v4.5.1

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!