Icon

Group Project_​Final_​Team 25

3. MODELS :

  • Random Forest

  • Logistic Regression

  • Decision Tree

1. DATA UNDERSTANDING :

  • Statistics analysis

  • Imbalance analysis

  • Histograms, boxplots & matrices

Step n°1 : Statistics & distribution analysis

Step n°2 : Visualisations

2. PREPROCESSING :

  • CSV import

  • Column selection

  • Missing values

  • Normalization

Gradient boosting validation and important metrics
Random forest validation and important metrics
Decision tree validation and important metrics
Comparing the performance metrics of the models
Champion model testing and important metrics
Upload the score data set to predict the missing target variable with the champion model.
Feature preparation
Logistic regression validation and important metrics

TEST BRANCH

VALIDATION BRANCH

TRAIN BRANCH

Selecting best F2 cut-off
Top k Row Filter
Lift Chart (JavaScript) (legacy)
ROC Curve (JavaScript) (legacy)
Generating F2
Precision & Recall
Decision Tree Learner
Joins 4 models
Joiner
Adjust prediction based on cutoff value of your champion AI model
Column Expressions (legacy)
Column Filter
Joins 2 models
Joiner
Number to String
Gradient Boosted Trees Learner
Validation
Gradient Boosted Trees Predictor
Descr + graphs
Data Explorer
Median imputation
Missing Value (Apply)
Value Counter
Statistics
Winsorizing
Numeric Outliers (Apply)
Distribution of vehicle age
Histogram
Confusion matrix and ROC
Binary Classification Inspector
Outliers in claim payout
Box Plot
Estimated claim payout compared to number of vehicles
Histogram
Scorer (JavaScript)
Driver liability % compared to number of claims
Histogram
Scorer (JavaScript)
Numerical variables
Column Filter
Scorer (JavaScript)
select top 3 models based on f2 score
Top k Row Filter
Scorer (JavaScript)
Multicollinearity
Linear Correlation
CSV Reader
auto_claims_score.csv (Data set for scoring)
CSV Reader
Create an Excel file with the model's outputs
Excel Writer
Selecting best F2 cut-off
Top k Row Filter
Lift Chart (JavaScript) (legacy)
Validation
Logistic Regression Predictor
ROC Curve (JavaScript) (legacy)
Boxplot of vehicle price
Box Plot
Outliers in annual income
Box Plot
Categorical variables
Column Filter
Median imputation
Missing Value (Apply)
Median imputation
Missing Value (Apply)
Validation 30%Test 10%
Table Partitioner
median imputation
Missing Value
Lift & Gain table
RowID
Validation
Gradient Boosted Trees Predictor
Validation
Random Forest Predictor
Winsorizing
Numeric Outliers
Winsorizing
Numeric Outliers (Apply)
lift chart
Line Plot (JavaScript) (legacy)
Generating F2
Precision & Recall
Lift Chart (JavaScript) (legacy)
Selecting best F2 cut-off
Top k Row Filter
ROC Curve (JavaScript) (legacy)
Generating F2
Precision & Recall
Winsorizing
Numeric Outliers (Apply)
Joins 2 models
Joiner
z-score standardisation
Normalizer
Extract Header & Transpose
Sert Color
z-score standardisation
Normalizer (Apply)
Column Filter
Binary Classification Inspector
Column Renamer
Generating F2
Precision & Recall
Number to String
Selecting best F2 cut-off
Top k Row Filter
Train 60%Remainder 40%
Table Partitioner
Lift Meta node
Logistic Regression Learner
Precision & Recall
Lift Chart (JavaScript) (legacy)
Validation
Decision Tree Predictor
Random Forest Learner
ROC Curve (JavaScript) (legacy)

Nodes

Extensions

Links