Scribd Logo
Upload

Welcome to Scribd!

  • Data Mining Project - 27.06.2021

    Uploaded by

    vansh gupta
    250 views6 pages
    This document is a business report for a data mining project containing two problems and their solutions. Problem 1 involves using clustering algorithms like hierarchical and K-means clustering on credit card customer data to identify segments for promotional offers. Problem 2 deals with building classification models like CART, Random Forest, and ANN on insurance claim data to predict claim status and provide recommendations. The Random Forest model performed the best with high accuracy and minimum deviation between training and test sets. Insights from the analysis suggest there will likely be more insurance claims this year and customer responses may increase with promotional offers and advertisements.

    Original Description:

    Original Title

    Data Mining Project_27.06.2021

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Report this Document
    This document is a business report for a data mining project containing two problems and their solutions. Problem 1 involves using clustering algorithms like hierarchical and K-means clustering on credit card customer data to identify segments for promotional offers. Problem 2 deals with building classification models like CART, Random Forest, and ANN on insurance claim data to predict claim status and provide recommendations. The Random Forest model performed the best with high accuracy and minimum deviation between training and test sets. Insights from the analysis suggest there will likely be more insurance claims this year and customer responses may increase with promotional offers and advertisements.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as docx, pdf, or txt
    250 views6 pages

    Data Mining Project - 27.06.2021

    Uploaded by

    vansh gupta
    This document is a business report for a data mining project containing two problems and their solutions. Problem 1 involves using clustering algorithms like hierarchical and K-means clustering on credit card customer data to identify segments for promotional offers. Problem 2 deals with building classification models like CART, Random Forest, and ANN on insurance claim data to predict claim status and provide recommendations. The Random Forest model performed the best with high accuracy and minimum deviation between training and test sets. Insights from the analysis suggest there will likely be more insurance claims this year and customer responses may increase with promotional offers and advertisements.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as docx, pdf, or txt
    of 6

    Data Mining

    Project

    Business Report

    27.06.2021

    Rakshit Tibrewal

    1
    Index

    Contents Page Number


    Problem 1 3
    Problem 2 4-5
    Thank you 6

    2
    Problem 1:

    A leading bank wants to develop a customer segmentation to give promotional offers to its
    customers. They collected a sample that summarizes the activities of users during the past few
    months. You are given the task to identify the segments based on credit card usage.

    1.1 Read the data, do the necessary initial steps, and exploratory data analysis (Univariate, Bi-
    variate, and multivariate analysis).

    Solution:

    Refer python file ‘Problem 1 Solution’

    1.2 Do you think scaling is necessary for clustering in this case? Justify

    Solution:

    Yes, Scaling of data is necessary maintain the same standardize data in the bank marketing dataset.

    1.3 Apply hierarchical clustering to scaled data. Identify the number of optimum clusters using
    Dendrogram and briefly describe them

    Solution:

    Refer python file ‘Problem 1 Solution’

    1.4 Apply K-Means clustering on scaled data and determine optimum clusters. Apply elbow curve
    and silhouette score. Explain the results properly. Interpret and write inferences on the finalized
    clusters.

    Solution:

    1.5 Describe cluster profiles for the clusters defined. Recommend different promotional strategies
    for different clusters.

    Solution:

    3
    Problem 2:

    An Insurance firm providing tour insurance is facing higher claim frequency. The management
    decides to collect data from the past few years. You are assigned the task to make a model which
    predicts the claim status and provide recommendations to management. Use CART, RF & ANN and
    compare the models' performances in train and test sets.

    2.1 Read the data, do the necessary initial steps, and exploratory data analysis (Univariate, Bi-
    variate, and multivariate analysis).

    Solution:

    Refer the file ‘Problem 2 Solution ANN’.

    2.2 Data Split: Split the data into test and train, build classification model CART, Random Forest,
    Artificial Neural Network

    Solution:

    CART Model

    Refer the file ‘Problem 2 Solution CART’

    Random Forest Model

    Refer the file ‘Problem 2 Solution_RF’

    Artificial Neural Network

    Refer the file ‘Problem 2 Solution ANN’.

    2.3 Performance Metrics: Comment and Check the performance of Predictions on Train and Test sets
    using Accuracy, Confusion Matrix, Plot ROC curve and get ROC_AUC score, classification reports for
    each model. 

    Solution:

    CART Random Forest Artificial Neural


    Model

    Test AUC: 79.2% AUC: 81.4% AUC: 81.4%

    Accuracy: 76% Accuracy: 76% Accuracy: 77%

    Train AUC: 86.4% AUC: 83.4% AUC: 79.3%

    Accuracy: 81% Accuracy: 79% Accuracy: 81%

    4
    2.4 Final Model: Compare all the models and write an inference which model is best/optimized.

    Solution:

    The Random forest model and ANN model has given highest performance compared to CART model.
    The deviation between training and testing dataset CART model is not ideal model to use. The ANN
    model has given second best performance as compared with random forest model based on the
    accuracy percentages. The Random forest model is the best fit with high accuracy percentages
    among other models, the percentage deviation between training and testing data set is 3% which
    minimum as compared with other models.

    2.5 Inference: Based on the whole Analysis, what are the business insights and recommendations?

    Solution:

    The purpose for the above case problem is to develop a predictive model to predict if an insurance
    firm providing tour insurance is facing higher claim frequency. As per prediction there is a probability
    there will be more claim in this year as per AUC and ROC area curve. The customer will responses
    will increase if they insurance policy is offered via promotions and advertisements.

    5
    Thank
    You
    6

    You might also like