Transcript Document
A GACP and GTMCP company How to perform predictive analysis on your web analytics tool data January 23rd, 2014 7/18/2015 #tatvicwebinar 3 Type of Analytics… A GACP and GTMCP company Descriptive: What has happened? Analytics Predictive: Predicts the outcome or future 7/18/2015 Prescriptive: What should happen? #tatvicwebinar Scope for Today A GACP and GTMCP company Descriptive: What has happened? Analytics Predictive: Predicts the outcome or future 7/18/2015 Prescriptive: What should happen? #tatvicwebinar In other words… A GACP and GTMCP company Predictive Analytics “Technology that learns from experience (data) to predict the future behavior of individuals in order to drive better decisions.” Source: Siegel, E. (2013) “Predictive Analytics. The power to predict who will click, buy, lie or die.” 7/18/2015 #tatvicwebinar Why it matters 7/18/2015 A GACP and GTMCP company #tatvicwebinar Applications 7/18/2015 A GACP and GTMCP company #tatvicwebinar Generic mental model A GACP and GTMCP company • Individual suggestions, preferences , clustering, & reaction of cohort to stimuli • Predict Failures, errors that costs big • Economic Value of Prediction 7/18/2015 #tatvicwebinar Myth Busting A GACP and GTMCP company • You don’t need to be a PhD statistician to build predictive models • A predictive model shouldn’t be a black box • Even if you know your data, modeling can help • Predictive models can be implemented quickly • Predictive models enhance human judgment, not replace it 7/18/2015 #tatvicwebinar Outline A GACP and GTMCP company Predictive Analytics 7/18/2015 Tool Data Model R Google Analytics Logistic Regression #tatvicwebinar Outline A GACP and GTMCP company Predictive Analytics Tool Data Model R Google Analytics Logistic Regression Visualization 7/18/2015 #tatvicwebinar Introduction to R What A GACP and GTMCP company • Open source statistical computing language, widely used by organizations to solve business problems. • Data Analysis • Statistical Tests • Data Visualization • Predictive Model • Easy to integrate • Data frame • • Choose and download a user-friendly GUI • Forecasting Applications Why How to get started 7/18/2015 Download and install • Pre developed packages RStudio #tatvicwebinar R Packages Categories of Packages Data Extraction A GACP and GTMCP company For this webinar • RGoogleAnalytics Usage: To extract Google Analytics data into R Contibutors: Michael Pearmain, Nick Mihailovski, Amar Gondaliya and Vignesh Prajapati Data Visualization • ggplot2 Usage: Build plots and charts Contibutor: Hadley Wickham Time Series Machine Learning 7/18/2015 #tatvicwebinar Outline of this webinar A GACP and GTMCP company Predictive Analytics Tool Data Model R Google Analytics Logistic Regression Visualization 7/18/2015 #tatvicwebinar Outline of this webinar A GACP and GTMCP company Predictive Analytics Tool Data Model R Google Analytics Logistic Regression Visualization 7/18/2015 #tatvicwebinar Google Analytics data A GACP and GTMCP company Extracting your GA data into R User performing data extraction Google OAuth2 Authorization Server Google Analytics API Access Token Request Access Token Response Call API for list of profiles Call API for query 7/18/2015 #tatvicwebinar Business Problem A GACP and GTMCP company Product return “Returns are on the rise-up 19% from 2007. For every US$1 spent on merchandize, 9¢ are returned.” “Average return rate for ecommerce retailers varies from 3-12%.” Source: Time Magazine, Sept. 04th, 2012 Product Return Impact (per day) Average Return Rate 9% 7% Average Order Value $100 $100 Orders Per Day 500 500 Total Income $50,000 $50,000 Loss due to returns $4,500 $3,500 Revenue post loss $45,500 $46,500 ----- $1000 Increase in Revenue/day 7/18/2015 Increase in Revenue with recovered returns in long run Month x30 $30,000 Year x365 $365,000 #tatvicwebinar Outline of this webinar A GACP and GTMCP company Predictive Analytics Tool Data Model R Google Analytics Logistic Regression Visualization 7/18/2015 #tatvicwebinar Data Introduction A GACP and GTMCP company Transactional Data 7/18/2015 Pre Purchase Data Browsing Behavior up to shopping cart In Purchase Data Purchase Behavior from shopping cart to thank you page Post Purchase Data Delivery Period, Location, amount of time to deliver, #tatvicwebinar Modeling A GACP and GTMCP company Loading Input Data Introducing Model Variables Model Creation Model Performance Applying Model to Test Data 7/18/2015 #tatvicwebinar Machine Learning Tech. A GACP and GTMCP company Supervised Learning Generates a function that maps inputs (labeled data) to desired outputs (e.g. Spam Detection) Variables Supervised Learning Model Labels are right answers from historical data Training Data Machine Learning Algorithm Labels eg. Spam Detector Input Data: Contains emails marked Spam/No Spam Variables Test Data 7/18/2015 Predictive Model Predicted Outcome labels #tatvicwebinar Modeling A GACP and GTMCP company Loading Input Data Introducing Model Variables Model Creation Model Performance Applying Model to Test Data 7/18/2015 #tatvicwebinar Modeling A GACP and GTMCP company Loading Input Data Introducing Model Variables Model Creation Model Performance Applying Model to Test Data 7/18/2015 #tatvicwebinar Feature engineering A GACP and GTMCP company Going beyond algorithms and using domain knowledge to augment new variables to model • • • • E.g.: Products purchased as gifts are less likely to be returned Create a New Variable with binary values: 1 – Product purchased as gift, 0 – otherwise Products purchased in holiday season are more likely to be returned Based on Purchase date, create new variable with binary values: 1 – Product purchased in the month Nov-Dec, 0 - otherwise 7/18/2015 #tatvicwebinar Predictor/Response Variables A GACP and GTMCP company 700,000.00 Price of House ($) Response Variable 800,000.00 600,000.00 500,000.00 400,000.00 300,000.00 200,000.00 100,000.00 0.00 0 500 1,000 1,500 2,000 2,500 3,000 Size of House (sq ft) 3,500 4,000 4,500 5,000 Predictor Variable 7/18/2015 #tatvicwebinar Modeling A GACP and GTMCP company Loading Input Data Introducing Model Variables Model Creation Model Performance Applying Model to Test Data 7/18/2015 #tatvicwebinar Generalized Linear Models A GACP and GTMCP company glm (formula, family, data) Formula Response ~ Predictor (This argument shows which all variables are independent (predictor) variables and which variable is/are dependent(response) variable/s Family Binomial (Since the output variable (which is product return is defined as binary value 0 or 1, we are using binomial family) Data Train data set – This data set consists values of all 18 variables (i.e. values of dependent variables and independent variables are given). This dataset is also called labeled data. 7/18/2015 #tatvicwebinar Modeling A GACP and GTMCP company Loading Input Data Introducing Model Variables Model Creation Model Performance Applying Model to Test Data 7/18/2015 #tatvicwebinar Modeling A GACP and GTMCP company Loading Input Data Introducing Model Variables Model Creation Model Performance Applying Model to Test Data 7/18/2015 #tatvicwebinar Machine Learning Tech. A GACP and GTMCP company Supervised Learning Generates a function that maps inputs (labeled data) to desired outputs (e.g. Spam Detection) Variables Supervised Learning Model Labels are right answers from historical data Training Data Machine Learning Algorithm Labels e.g.: Spam Detector Input Data: Contains emails marked Spam/No Spam Variables Test Data 7/18/2015 Predictive Model Predicted Outcome labels #tatvicwebinar Summary A GACP and GTMCP company Probability of product return > 60% Number of Transactions Probability of product return ≤ 60% > 60 % ≤ 60 % > 60 % < 60 % Probability of Product Returns Call customer before shipping Send discount coupon to initiate customer for future purchase 7/18/2015 #tatvicwebinar Myth Busting A GACP and GTMCP company • You don’t need to be a PhD statistician to build predictive models • A predictive model shouldn’t be a black box • Even if you know your data, modeling can help • Predictive models can be implemented quickly • Predictive models enhance human judgment, not replace it 7/18/2015 #tatvicwebinar A GACP and GTMCP company Thank you! 7/18/2015 #tatvicwebinar