SlideShare ist ein Scribd-Unternehmen logo
1 von 18
Downloaden Sie, um offline zu lesen
Capstone Project
1
ElecKart
Market Mix Modelling
Group Members:
Anuj Panchal
Bhaswati Paul
Pooja Manjarekar
Ashwini Ingale
2
Business & Data Understanding
Data preparation &
Exploratory Data Analysis
Features Engineering
Model Building & KPI
Recommendation
3
Objective
● To develop a market mix model for 3 product sub-categories
Camera accessory, Gaming accessory and Home Audio to
observe the actual impact of different marketing levers over
sale of last one year (July 2015 -June 2016) and recommend
the optimal budget allocation for different marketing levers
for the next year.
ElecKart is an e-commerce firm dealing mainly with electronic products
Our Understanding of the Scope
1
•Gather e-commerce domain knowledge
2
•Understand the given dataset and questions that can be
answered
3
•Cleaning and prepare the data; with 3 category-wise data sets
creation
4
•Derived variable creation and grouping by weeks
5
•EDA
6
•Uni and bi -variate analysis
7
•Multi-variate analysis; using different modeling techniques
8
•Choose the best model for each segment
4
Basic understanding of given data
5
•# of units sold
•Delivery days and SLA
•Categories/sub categories
•Vertical
•Procurement SLA
•Item type =
Luxury/Mass-Market
•Marketing Channel
Investments
•Customer sentiment
•Discounts
•Adstock
•gmv
•Product mrp
•Pin-code
•Order Payment Type
•Week of the year –
seasonality
•Holiday / Events; isHoliday
ConsumerElectronics
1. Removing all the rows having NA and duplicate values.
2. Checking unique values
3. Converting date column’s data type to DATE
4. Filtering out data which does not fall within the timelines of this analysis – 1st
July 2015 –
30th
June 2016.
5. Creating weeks from the ‘order_id’ data.
6. Converting order_id and order_item_id into proper numeric format - from scientific notation.
7. Removing rows with negative product MRP; gmv and units.
8. Removing rows where (product_mrp*unit) < gmv.
9. Removing rows with negative deliverybdays and deliverycdays; assuming “N” means no
delay.
10. Rarely SLA/procurement SLA for any delivery will be more than 2 months (60 days); hence
filtering out these value .
11. Computing discount % for each transaction.
12. Computing gvm/unit.
13. Computing ItemType – categorizing items into Luxury (priced more the 80 %tile) and Mass
Market.
14. Removing Columns which will not be used in analysis.
15. Storing the total gmv proportion for each of the 3 categories wrt the total gvm for all items
16. Filtering and keeping only the 3 required categories.
Data Cleaning and Preparation of consumer
Electronics
6
Media data and other information.xlsx
1. Loading all the 4 spreadsheets
2. Special Sale Calendar –
1. Splitting the event name and date; also converting the date in proper format.
2. Creating event start and end date.
3. Producing a dataframe – having all dates possible within the timeframe of analysis and
corresponding event names (if any).
4. Merging this with consumer data – produced earlier.
3. Monthly NPS Score –
1. Transposing the columns into rows.
2. Cleaning the naming issues wrt months.
3. Populating the same monthly scores to each day of the month.
4. Convert it to weekly basis.
5. Merging this with consumer data – produced earlier.
4. Media Investment –
1. Distributing the monthly investing data for each channel into daily investment – proportionate
to “days in that month”.
2. Converting it on weekly basis.
3. Extracting category-wise investment – proportionately to gvm of each of the 3 category wrt
the total gvm.
4. Creating 3 category-wise dataframes - Merging this with consumer data – produced earlier.
5. Converging CR(10000000) to Total Investment, TV, Digital, Sponsorship, Content-Marketing,
Online-Marketing, Affiliates, SEM, Radio, Other attributes.
5. Any item having gmv/unit more at 80%tile is assumed to be Luxury else Mass-market.
Please note: At the end of this analysis we are producing 3 category wise clean .csv .files
Data Cleaning Preparation of Media data
7
Local factors impacts: Ontario local holidays are considered
along with other holidays for said FY(July-15 to June-16).
Local Factors
8
9
Bar charts and Graphs of master dataframe
Units sold Special
day sales
Monthly
GMV
Weekly
holiday
sales
EDA (Camera Accessory)
10
Special holiday
sales
Weekday
sales
Weekly
sales
Weekly
payment types
EDA (Gaming Accessory)
11
Special holiday
sales
Weekday
sales
Weekly
sales
Weekly
discount %
12
EDA (Home Audio)
Special holiday
sales
Weekday
sales
Weekly
payment types
Weekly
sales
13
Adstock
Affiliates Digital TV
Online Marketing Other Radio
SEM Sponsorship
14
Derived KPIs & Modeling
List of derived KPIs and advance KPIs is as follows:
KPIs Advance KPIs
● Discount Percentage ● Ad-stock of 3 categories
● GMV per unit ● Moving average of last 3 weeks (gmv per
unit, DP)
● Total GMV ● Lag variables (gmv per unit, DP) for 3
weeks
● Average GMV ● Promotion Type
● Units ● Holiday Week
● Delivery Status ● Delivery Status
● Item Type
● Delivery on Time
15
Model Dashboard
Model/Category Camera Accessory Gaming Accessory Home Audio
Linear 0.89 0.86 0.78
Multiplicative 0.92 0.70 0.86
Koyck 0.86 0.87 0.75
Distributed Lag 0.86 0.86 0.76
r-square prediction values (without cross validation)
Model/Category Camera Accessory Gaming Accessory Home Audio
Linear 0.91 0.89 0.80
Multiplicative 0.88 0.72 0.92
Koyck 0.91 0.89 0.84
Distributed Lag 0.91 0.89 0.84
r-square prediction values (with cross validation)
● After analyzing 4 different models, its observed that Koyck model is best
suited for Camera Accessories.
● Its has least mean square error (0.007) and have high result in Cross
-Validation (0.91) as compare to other three models.
● product_mrp is the strongest variable having a good impact on the GMV.
● Other common factor which affect the model is delivery_on_time, Content
Marketing etc.
16
Camera Accessories – Recommendations
● After analyzing 3 different models, its observed that Koyck model is best
suited for Gaming Accessories.
● For Gaming Accessories, RMSE is 0.0071 for Koyck which is the least
mean square error as compared to others.
● Also product_mrp is the strongest variable having a good impact on the
GMV.
● Other common factor which affect the model is delivery_on_time, Content
Marketing etc
17
Gaming Accessories – Recommendations
● After building and analyzing 3 different models, it is observed that
Multiplicative model is best suited for the category of Home Audio.
● R2 scores of Koyck and Distributed lag models are almost the same but
better results are achieved after performing cross validation.
● product_mrp is the strongest variable having a good impact on the GMV.
● gmv_lag_1_per and gmv_lag_2_per are also proving to be good for GMV.
● GMV increases with a little bit of tweaking in the product_mrp.
18
Home Audio – Recommendations

Weitere ähnliche Inhalte

Was ist angesagt?

Final project
Final projectFinal project
Final project
ejw0062
 
How I have reached brand resonance with Nescafe
How I have reached brand resonance with NescafeHow I have reached brand resonance with Nescafe
How I have reached brand resonance with Nescafe
Mrittika Mirza
 

Was ist angesagt? (20)

Omnichannel guide
Omnichannel guideOmnichannel guide
Omnichannel guide
 
ASOS digital marketing strategy
ASOS digital marketing strategyASOS digital marketing strategy
ASOS digital marketing strategy
 
Starbucks marketing campaign analysis
Starbucks marketing campaign analysisStarbucks marketing campaign analysis
Starbucks marketing campaign analysis
 
Amazon
Amazon Amazon
Amazon
 
Nespresso
NespressoNespresso
Nespresso
 
NESPRESSO MARKETING ANALYSIS 2014
NESPRESSO MARKETING ANALYSIS 2014NESPRESSO MARKETING ANALYSIS 2014
NESPRESSO MARKETING ANALYSIS 2014
 
Birchbox presentation
Birchbox presentationBirchbox presentation
Birchbox presentation
 
Starbucks Vs Cafe Coffee Day - Understanding the Consumer Preferences
Starbucks Vs Cafe Coffee Day - Understanding the Consumer PreferencesStarbucks Vs Cafe Coffee Day - Understanding the Consumer Preferences
Starbucks Vs Cafe Coffee Day - Understanding the Consumer Preferences
 
Victoria's Secret
Victoria's Secret Victoria's Secret
Victoria's Secret
 
Final project
Final projectFinal project
Final project
 
Nespresso brand positioning
Nespresso brand positioningNespresso brand positioning
Nespresso brand positioning
 
Business strategy of starbucks coffee
Business strategy of starbucks coffeeBusiness strategy of starbucks coffee
Business strategy of starbucks coffee
 
A new coffee for the USA from Nestlé Nespresso
A new coffee for the USA from Nestlé NespressoA new coffee for the USA from Nestlé Nespresso
A new coffee for the USA from Nestlé Nespresso
 
VietNam entry mode of Starbuck
VietNam entry mode of StarbuckVietNam entry mode of Starbuck
VietNam entry mode of Starbuck
 
Amazon
AmazonAmazon
Amazon
 
Nespresso case study
Nespresso case studyNespresso case study
Nespresso case study
 
Case Study Nespresso
Case Study NespressoCase Study Nespresso
Case Study Nespresso
 
How I have reached brand resonance with Nescafe
How I have reached brand resonance with NescafeHow I have reached brand resonance with Nescafe
How I have reached brand resonance with Nescafe
 
Marketing as an INFJ: How Understanding Your Personality Type Makes You a Bet...
Marketing as an INFJ: How Understanding Your Personality Type Makes You a Bet...Marketing as an INFJ: How Understanding Your Personality Type Makes You a Bet...
Marketing as an INFJ: How Understanding Your Personality Type Makes You a Bet...
 
Amazon India ppt
Amazon India pptAmazon India ppt
Amazon India ppt
 

Ähnlich wie CapstoneProjectPresentation.pdf

Mba 433 MIS - Data Warehouse
Mba 433 MIS - Data WarehouseMba 433 MIS - Data Warehouse
Mba 433 MIS - Data Warehouse
Vinita Prasad
 
ContentsPhase 1 Design Concepts2Project Description2Use.docx
ContentsPhase 1 Design Concepts2Project Description2Use.docxContentsPhase 1 Design Concepts2Project Description2Use.docx
ContentsPhase 1 Design Concepts2Project Description2Use.docx
maxinesmith73660
 
The Barclays Data Science Hackathon: Building Retail Recommender Systems base...
The Barclays Data Science Hackathon: Building Retail Recommender Systems base...The Barclays Data Science Hackathon: Building Retail Recommender Systems base...
The Barclays Data Science Hackathon: Building Retail Recommender Systems base...
Data Science Milan
 
Copyright © 2014 EMC Corporation. All rights reserved.Copy.docx
Copyright © 2014 EMC Corporation. All rights reserved.Copy.docxCopyright © 2014 EMC Corporation. All rights reserved.Copy.docx
Copyright © 2014 EMC Corporation. All rights reserved.Copy.docx
dickonsondorris
 
Case Study Scenario - Global Trading PLCGlobal Trading PLC is.docx
Case Study Scenario - Global Trading PLCGlobal Trading PLC is.docxCase Study Scenario - Global Trading PLCGlobal Trading PLC is.docx
Case Study Scenario - Global Trading PLCGlobal Trading PLC is.docx
tidwellveronique
 
DATA MINING MODEL PERFORMANCE OF SALES PREDICTIVE ALGORITHMS BASED ON RAPIDMI...
DATA MINING MODEL PERFORMANCE OF SALES PREDICTIVE ALGORITHMS BASED ON RAPIDMI...DATA MINING MODEL PERFORMANCE OF SALES PREDICTIVE ALGORITHMS BASED ON RAPIDMI...
DATA MINING MODEL PERFORMANCE OF SALES PREDICTIVE ALGORITHMS BASED ON RAPIDMI...
AIRCC Publishing Corporation
 
DATA MINING MODEL PERFORMANCE OF SALES PREDICTIVE ALGORITHMS BASED ON RAPIDMI...
DATA MINING MODEL PERFORMANCE OF SALES PREDICTIVE ALGORITHMS BASED ON RAPIDMI...DATA MINING MODEL PERFORMANCE OF SALES PREDICTIVE ALGORITHMS BASED ON RAPIDMI...
DATA MINING MODEL PERFORMANCE OF SALES PREDICTIVE ALGORITHMS BASED ON RAPIDMI...
ijcsit
 

Ähnlich wie CapstoneProjectPresentation.pdf (20)

IRJET- Finding Optimal Skyline Product Combinations Under Price Promotion
IRJET- Finding Optimal Skyline Product Combinations Under Price PromotionIRJET- Finding Optimal Skyline Product Combinations Under Price Promotion
IRJET- Finding Optimal Skyline Product Combinations Under Price Promotion
 
Mba 433 MIS - Data Warehouse
Mba 433 MIS - Data WarehouseMba 433 MIS - Data Warehouse
Mba 433 MIS - Data Warehouse
 
Building ML models for smart retail
Building ML models for smart retailBuilding ML models for smart retail
Building ML models for smart retail
 
Customer Decision Support System
Customer Decision Support SystemCustomer Decision Support System
Customer Decision Support System
 
ContentsPhase 1 Design Concepts2Project Description2Use.docx
ContentsPhase 1 Design Concepts2Project Description2Use.docxContentsPhase 1 Design Concepts2Project Description2Use.docx
ContentsPhase 1 Design Concepts2Project Description2Use.docx
 
The Barclays Data Science Hackathon: Building Retail Recommender Systems base...
The Barclays Data Science Hackathon: Building Retail Recommender Systems base...The Barclays Data Science Hackathon: Building Retail Recommender Systems base...
The Barclays Data Science Hackathon: Building Retail Recommender Systems base...
 
Copyright © 2014 EMC Corporation. All rights reserved.Copy.docx
Copyright © 2014 EMC Corporation. All rights reserved.Copy.docxCopyright © 2014 EMC Corporation. All rights reserved.Copy.docx
Copyright © 2014 EMC Corporation. All rights reserved.Copy.docx
 
Data Visualization: Sales forecasting
Data Visualization: Sales forecastingData Visualization: Sales forecasting
Data Visualization: Sales forecasting
 
CoreBigBench: Benchmarking Big Data Core Operations
CoreBigBench: Benchmarking Big Data Core OperationsCoreBigBench: Benchmarking Big Data Core Operations
CoreBigBench: Benchmarking Big Data Core Operations
 
CoreBigBench: Benchmarking Big Data Core Operations
CoreBigBench: Benchmarking Big Data Core OperationsCoreBigBench: Benchmarking Big Data Core Operations
CoreBigBench: Benchmarking Big Data Core Operations
 
Price proposal.10.2014
Price proposal.10.2014Price proposal.10.2014
Price proposal.10.2014
 
Case Study Scenario - Global Trading PLCGlobal Trading PLC is.docx
Case Study Scenario - Global Trading PLCGlobal Trading PLC is.docxCase Study Scenario - Global Trading PLCGlobal Trading PLC is.docx
Case Study Scenario - Global Trading PLCGlobal Trading PLC is.docx
 
DATA MINING MODEL PERFORMANCE OF SALES PREDICTIVE ALGORITHMS BASED ON RAPIDMI...
DATA MINING MODEL PERFORMANCE OF SALES PREDICTIVE ALGORITHMS BASED ON RAPIDMI...DATA MINING MODEL PERFORMANCE OF SALES PREDICTIVE ALGORITHMS BASED ON RAPIDMI...
DATA MINING MODEL PERFORMANCE OF SALES PREDICTIVE ALGORITHMS BASED ON RAPIDMI...
 
DATA MINING MODEL PERFORMANCE OF SALES PREDICTIVE ALGORITHMS BASED ON RAPIDMI...
DATA MINING MODEL PERFORMANCE OF SALES PREDICTIVE ALGORITHMS BASED ON RAPIDMI...DATA MINING MODEL PERFORMANCE OF SALES PREDICTIVE ALGORITHMS BASED ON RAPIDMI...
DATA MINING MODEL PERFORMANCE OF SALES PREDICTIVE ALGORITHMS BASED ON RAPIDMI...
 
IT - NORWAY
IT - NORWAYIT - NORWAY
IT - NORWAY
 
Optimal management presentation for investors about supply chains optimization
Optimal management presentation for investors about supply chains optimizationOptimal management presentation for investors about supply chains optimization
Optimal management presentation for investors about supply chains optimization
 
laptop price prediction presentation
laptop price prediction presentationlaptop price prediction presentation
laptop price prediction presentation
 
Intro to Data warehousing lecture 15
Intro to Data warehousing   lecture 15Intro to Data warehousing   lecture 15
Intro to Data warehousing lecture 15
 
Delivering Personalized Experiences using the Power of Data
Delivering Personalized Experiences using the Power of Data Delivering Personalized Experiences using the Power of Data
Delivering Personalized Experiences using the Power of Data
 
BA_CEC.pptx
BA_CEC.pptxBA_CEC.pptx
BA_CEC.pptx
 

Kürzlich hochgeladen

Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
amitlee9823
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
amitlee9823
 
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night StandCall Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...
Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...
Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...
amitlee9823
 
Probability Grade 10 Third Quarter Lessons
Probability Grade 10 Third Quarter LessonsProbability Grade 10 Third Quarter Lessons
Probability Grade 10 Third Quarter Lessons
JoseMangaJr1
 
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night StandCall Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
amitlee9823
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
amitlee9823
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
amitlee9823
 
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
amitlee9823
 
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
ZurliaSoop
 
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al BarshaAl Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
AroojKhan71
 

Kürzlich hochgeladen (20)

Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
 
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night StandCall Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
 
Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...
Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...
Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...
 
Probability Grade 10 Third Quarter Lessons
Probability Grade 10 Third Quarter LessonsProbability Grade 10 Third Quarter Lessons
Probability Grade 10 Third Quarter Lessons
 
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night StandCall Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 
Anomaly detection and data imputation within time series
Anomaly detection and data imputation within time seriesAnomaly detection and data imputation within time series
Anomaly detection and data imputation within time series
 
Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -
Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -
Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -
 
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
 
BigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxBigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptx
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signals
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFx
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
 
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
 
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
 
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al BarshaAl Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
 
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Research
 

CapstoneProjectPresentation.pdf

  • 1. Capstone Project 1 ElecKart Market Mix Modelling Group Members: Anuj Panchal Bhaswati Paul Pooja Manjarekar Ashwini Ingale
  • 2. 2 Business & Data Understanding Data preparation & Exploratory Data Analysis Features Engineering Model Building & KPI Recommendation
  • 3. 3 Objective ● To develop a market mix model for 3 product sub-categories Camera accessory, Gaming accessory and Home Audio to observe the actual impact of different marketing levers over sale of last one year (July 2015 -June 2016) and recommend the optimal budget allocation for different marketing levers for the next year.
  • 4. ElecKart is an e-commerce firm dealing mainly with electronic products Our Understanding of the Scope 1 •Gather e-commerce domain knowledge 2 •Understand the given dataset and questions that can be answered 3 •Cleaning and prepare the data; with 3 category-wise data sets creation 4 •Derived variable creation and grouping by weeks 5 •EDA 6 •Uni and bi -variate analysis 7 •Multi-variate analysis; using different modeling techniques 8 •Choose the best model for each segment 4
  • 5. Basic understanding of given data 5 •# of units sold •Delivery days and SLA •Categories/sub categories •Vertical •Procurement SLA •Item type = Luxury/Mass-Market •Marketing Channel Investments •Customer sentiment •Discounts •Adstock •gmv •Product mrp •Pin-code •Order Payment Type •Week of the year – seasonality •Holiday / Events; isHoliday
  • 6. ConsumerElectronics 1. Removing all the rows having NA and duplicate values. 2. Checking unique values 3. Converting date column’s data type to DATE 4. Filtering out data which does not fall within the timelines of this analysis – 1st July 2015 – 30th June 2016. 5. Creating weeks from the ‘order_id’ data. 6. Converting order_id and order_item_id into proper numeric format - from scientific notation. 7. Removing rows with negative product MRP; gmv and units. 8. Removing rows where (product_mrp*unit) < gmv. 9. Removing rows with negative deliverybdays and deliverycdays; assuming “N” means no delay. 10. Rarely SLA/procurement SLA for any delivery will be more than 2 months (60 days); hence filtering out these value . 11. Computing discount % for each transaction. 12. Computing gvm/unit. 13. Computing ItemType – categorizing items into Luxury (priced more the 80 %tile) and Mass Market. 14. Removing Columns which will not be used in analysis. 15. Storing the total gmv proportion for each of the 3 categories wrt the total gvm for all items 16. Filtering and keeping only the 3 required categories. Data Cleaning and Preparation of consumer Electronics 6
  • 7. Media data and other information.xlsx 1. Loading all the 4 spreadsheets 2. Special Sale Calendar – 1. Splitting the event name and date; also converting the date in proper format. 2. Creating event start and end date. 3. Producing a dataframe – having all dates possible within the timeframe of analysis and corresponding event names (if any). 4. Merging this with consumer data – produced earlier. 3. Monthly NPS Score – 1. Transposing the columns into rows. 2. Cleaning the naming issues wrt months. 3. Populating the same monthly scores to each day of the month. 4. Convert it to weekly basis. 5. Merging this with consumer data – produced earlier. 4. Media Investment – 1. Distributing the monthly investing data for each channel into daily investment – proportionate to “days in that month”. 2. Converting it on weekly basis. 3. Extracting category-wise investment – proportionately to gvm of each of the 3 category wrt the total gvm. 4. Creating 3 category-wise dataframes - Merging this with consumer data – produced earlier. 5. Converging CR(10000000) to Total Investment, TV, Digital, Sponsorship, Content-Marketing, Online-Marketing, Affiliates, SEM, Radio, Other attributes. 5. Any item having gmv/unit more at 80%tile is assumed to be Luxury else Mass-market. Please note: At the end of this analysis we are producing 3 category wise clean .csv .files Data Cleaning Preparation of Media data 7
  • 8. Local factors impacts: Ontario local holidays are considered along with other holidays for said FY(July-15 to June-16). Local Factors 8
  • 9. 9 Bar charts and Graphs of master dataframe Units sold Special day sales Monthly GMV Weekly holiday sales
  • 10. EDA (Camera Accessory) 10 Special holiday sales Weekday sales Weekly sales Weekly payment types
  • 11. EDA (Gaming Accessory) 11 Special holiday sales Weekday sales Weekly sales Weekly discount %
  • 12. 12 EDA (Home Audio) Special holiday sales Weekday sales Weekly payment types Weekly sales
  • 13. 13 Adstock Affiliates Digital TV Online Marketing Other Radio SEM Sponsorship
  • 14. 14 Derived KPIs & Modeling List of derived KPIs and advance KPIs is as follows: KPIs Advance KPIs ● Discount Percentage ● Ad-stock of 3 categories ● GMV per unit ● Moving average of last 3 weeks (gmv per unit, DP) ● Total GMV ● Lag variables (gmv per unit, DP) for 3 weeks ● Average GMV ● Promotion Type ● Units ● Holiday Week ● Delivery Status ● Delivery Status ● Item Type ● Delivery on Time
  • 15. 15 Model Dashboard Model/Category Camera Accessory Gaming Accessory Home Audio Linear 0.89 0.86 0.78 Multiplicative 0.92 0.70 0.86 Koyck 0.86 0.87 0.75 Distributed Lag 0.86 0.86 0.76 r-square prediction values (without cross validation) Model/Category Camera Accessory Gaming Accessory Home Audio Linear 0.91 0.89 0.80 Multiplicative 0.88 0.72 0.92 Koyck 0.91 0.89 0.84 Distributed Lag 0.91 0.89 0.84 r-square prediction values (with cross validation)
  • 16. ● After analyzing 4 different models, its observed that Koyck model is best suited for Camera Accessories. ● Its has least mean square error (0.007) and have high result in Cross -Validation (0.91) as compare to other three models. ● product_mrp is the strongest variable having a good impact on the GMV. ● Other common factor which affect the model is delivery_on_time, Content Marketing etc. 16 Camera Accessories – Recommendations
  • 17. ● After analyzing 3 different models, its observed that Koyck model is best suited for Gaming Accessories. ● For Gaming Accessories, RMSE is 0.0071 for Koyck which is the least mean square error as compared to others. ● Also product_mrp is the strongest variable having a good impact on the GMV. ● Other common factor which affect the model is delivery_on_time, Content Marketing etc 17 Gaming Accessories – Recommendations
  • 18. ● After building and analyzing 3 different models, it is observed that Multiplicative model is best suited for the category of Home Audio. ● R2 scores of Koyck and Distributed lag models are almost the same but better results are achieved after performing cross validation. ● product_mrp is the strongest variable having a good impact on the GMV. ● gmv_lag_1_per and gmv_lag_2_per are also proving to be good for GMV. ● GMV increases with a little bit of tweaking in the product_mrp. 18 Home Audio – Recommendations