Scribd Logo
Upload

Welcome to Scribd!

  • MRA ML1 Plabeeta Patangia

    Uploaded by

    Plabeeta Patangia
    2K views30 pages
    This document summarizes an analysis of customer transaction data for an automobile parts company. The analysis includes exploratory data analysis of the transaction data to understand patterns. A RFM customer segmentation model is developed using KNIME to categorize customers into segments like best customers, customers at risk of churning, lost customers and loyal customers based on recency, frequency and monetary value of transactions. The analysis identifies the top customers in each segment to help the company focus its retention and acquisition strategies.

    Original Description:

    MRA ML1

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Report this Document
    This document summarizes an analysis of customer transaction data for an automobile parts company. The analysis includes exploratory data analysis of the transaction data to understand patterns. A RFM customer segmentation model is developed using KNIME to categorize customers into segments like best customers, customers at risk of churning, lost customers and loyal customers based on recency, frequency and monetary value of transactions. The analysis identifies the top customers in each segment to help the company focus its retention and acquisition strategies.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as pptx, pdf, or txt
    2K views30 pages

    MRA ML1 Plabeeta Patangia

    Uploaded by

    Plabeeta Patangia
    This document summarizes an analysis of customer transaction data for an automobile parts company. The analysis includes exploratory data analysis of the transaction data to understand patterns. A RFM customer segmentation model is developed using KNIME to categorize customers into segments like best customers, customers at risk of churning, lost customers and loyal customers based on recency, frequency and monetary value of transactions. The analysis identifies the top customers in each segment to help the company focus its retention and acquisition strategies.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as pptx, pdf, or txt
    of 30

    MRA PROJECT

    MILESTONE 1
    PLABEETA PATANGIA
    BATCH : DSBA DEC 20 GROUP 1
    EMAIL : [email protected]
    TABLE OF CONTENT
     Problem Statement
     Exploratory Data Analysis
    • Data Info, Shape, Summary
    • Univariate, Bivariate & Multivariate Analysis

     Customer Segmentation Using RFM Analysis


    • Tools Used & Assumptions Made
    • Output Table
    • KNIME Workfolw

     RFM Inferences and Identified


    • Best Customers
    • Customers on the Verge of Churning
    • Lost Customers
    • Loyal Customers
    PROBLEM
    STATEMENT
    • An automobile parts manufacturing company has collected data of transactions for 3 years. They do not have
    any in-house data science team; thus, they have hired you as their consultant. Your job is to use your magical
    data science skills to provide them with suitable insights about their data and their customers.
    • Auto Sales Data: Sales_Data.xlsx
    EXPLORATORY DATA ANALYSIS

     Info  Data Shape


    The data has 2747 instances with 19 attributes. 2
    Float type , 5 integer type and 13 Object type as  There are no null values which is
    evident from the below result. evident from the below result.
    EXPLORATORY DATA ANALYSIS
     Description

    Following is the summary of the summary of the data that gives us the information on all the basic
    statistics Metrices.
    EXPLORATORY DATA ANALYSIS

    Distribution Graph and Outlier detection of the continuous variables:

    Price of Each Product


    EXPLORATORY DATA ANALYSIS

    Distribution Graph and Outlier detection of the continuous variables:

    Quantity Order for Each Product


    EXPLORATORY DATA ANALYSIS

    Distribution Graph and Outlier detection of the continuous variables:

     Manufacturer's Suggested Retail Price


    EXPLORATORY DATA ANALYSIS

    Distribution Graph and Outlier detection of the continuous variables:

    Sales for Each Product


    EXPLORATORY DATA ANALYSIS

    Correlation
     Heatmap of the Correlation Matrix:

     Highly Correlated Values are :

     Sales & MSRP


     Sales & QuantityOrdered
     Sales & PriceEach
     MSRP & PriceEach
    EXPLORATORY DATA ANALYSIS

    Univariate Analysis
    EXPLORATORY DATA ANALYSIS
    Univariate Analysis
    EXPLORATORY DATA ANALYSIS
    Univariate Analysis
    EXPLORATORY DATA ANALYSIS
    Univariate Analysis
    EXPLORATORY DATA ANALYSIS
    Univariate Analysis
    EXPLORATORY DATA ANALYSIS

    Univariate Analysis
    Trend in Sales Summary

     November Month gives out the highest sales and week 45 falls in
    November which has the highest sales as compared to other weeks.
     Sales decreased from Q1 to Q3 and takes a huge rise on Q4.
     2019 seems to deliver highest Sales
    EXPLORATORY DATA ANALYSIS
    Bivariate Analysis
    EXPLORATORY DATA ANALYSIS
    Bivariate Analysis
    EXPLORATORY DATA ANALYSIS
    Bivariate Analysis
    EXPLORATORY DATA ANALYSIS
    Bivariate Analysis
    EXPLORATORY DATA ANALYSIS

    Inferences :

     USA has the Highest sales as compared to other countries.


     Classic Cars has the highest sales while Trains has the lowest.
     City Madrid in Spain has the Highest sales when compared to other cities
     The company is customer driven as the major Revenue is generated from only the top 5 customers.
    So the company must focus on more customer scouting as in case of client churn it will impact the
    sales.
     Euro Shopping Channel is the best customer in terms of Sales Amount.
     Medium Deal Size deliver higher sales than Small and Medium.
    CUSTOMER SEGMENTATION USING RFM ANALYSIS

     KNIME Tool is used for RFM Analysis and customer segmentation


     Customer Name, Quantity Ordered, PriceEach,OrderDate,Sales are used as parameters
     RFM Model
     Current Date – Max(Order Date) is taken as Recency Value
     Count of Quantity ordered for a given customer is taken as Frequency Value
     Sum of Sales made for a given customer is taken as Monetary Value
    CUSTOMER
    SEGMENTATION
    USING RFM ANALYSIS

    Output Table Head


    KNIME
    WORKFLOW
    INFERENCES FROM RFM ANALYSIS AND IDENTIFIED
    SEGMENTS

    best customers
    customers are on the verge of churning
    lost customers
    loyal customers
    INFERENCES FROM RFM ANALYSIS AND IDENTIFIED
    SEGMENTS
    Best customers
    • Euro Shopping Channel
    • Souveniers And Things Co.
    • Salzburg Collectables
    • Danish Wholesale Imports
    • La Rochelle Gifts
    • L'ordine Souveniers
    • The Sharp Gifts Warehouse
    INFERENCES FROM RFM ANALYSIS AND IDENTIFIED
    SEGMENTS
    Customers are on the verge of churning
    • Saveley & Henriot, Co.
    • Saveley & Henriot, Co.
    • Herkku Gifts
    • Marta's Replicas Co.
    • Vida Sport, Ltd
    INFERENCES FROM RFM ANALYSIS AND IDENTIFIED
    SEGMENTS
    Lost customers
    • Auto Assoc. & Cie.
    • Bavarian Collectables Imports, Co.
    • CAF Imports
    • Cambridge Collectables Co.
    • Clover Collections, Co.
    • Daedalus Designs Imports
    • Double Decker Gift Stores, Ltd
    • Iberia Gift Imports, Corp.
    INFERENCES FROM RFM ANALYSIS AND IDENTIFIED
    SEGMENTS

    Loyal customers
    • Handji Gifts& Co
    • Auto Canal Petit
    • Tokyo Collectables, Ltd
    • UK Collectables, Ltd.
    • Mini Gifts Distributors Ltd.
    THANK YOU

    You might also like