Retail Analytics Course

Learn about Hypothesis testing, the many Hypothesis testing Statistics, work with the Null Hypothesis & Alternative hypothesis and Types of hypothesis testing. Interpret the results of Hypothesis test and probabilities of Alpha error, understand Type I and Type II errors. Get introduced to Linear regression, various components of Linear regression viz regression line, Linear regression equation, the concept of Ordinary Least Square. Get introduced to Linear regression analysis, and Linear regression examples

Understand the Linear regression in a multivariate scenario, understand collinearity and how to deal with it. Get introduced to the analysis of Attribute Data, understand the principles of Logistic regression, Binary Logistic regression analysis. Learn about the Multiple Logistic regression, Probability measures, and its interpretation. Get clarity on the confusion matrix and its elements. Get introduced to “Cut off value” estimation using AUC and ROC curve, understand False Positive Rate, False Negative Rate, Sensitivity, Specificity. Gain a birds-eye view to various advanced regression techniques and analysis of count data namely Poisson regression, Negative binomial regression. Learn when to use Poisson regression and negative binomial regression for predicting count data.

At the end of this topic, you will learn about the applications & possibilities in the space of Retail & Supply Chain. You will also learn the possibilities of IoT applications in general and in particular in Retail & Supply Chain. Also, the analytics-driven landscape of digital marketing analytics in the space of Retail is explained in detail.

• Data Generation Sources
• Typical RSCA Process
• Data in RSCA
• Analytical Techniques in RSCA context
• Data Analytics & Decision-Making Models
• Promise of Advanced Analytics in Retail
• Introduction to IoT (Internet of Things)
• Applications of IoT in Retail
• Introduction to Contemporary Analytics

At the end of this topic, you will learn about the applications of Segmentation. You will learn about the techniques used to measure the similarity between the records. Understand how organizing and managing the entities (Products/Customers) will become so much easier and beneficial. You will learn the strategies that can be applied to segregate the data.

• Introduction to Segmentation/Clustering
• Clustering Techniques
• Distance measures to measure Similarity
• Clustering Approaches
  • Hierarchical Clustering
  • Non-Hierarchical Clustering
• Linkage Functions
• Within the Sum of Squares
• Elbow Curve
• Choosing the best number of Clusters

At the end of this topic, you will learn how to build a basic recommendation engine for any eCommerce portal. You will be able to appreciate the various strategies involved in building a recommendation engine to make the organization profitable. It will be a blend of theoretical concepts & usage of R programming to accomplish this practically.

• Introduction to Recommender Systems
• Traditional Collaborative Filtering
• Distance measures such as
  • Cosine-based similarity
  • Correlation-based similarity
• Strategy for Analytics Solution
  • Runtime vs. Quality of recommendation
  • Reducing Computation Burden
• Search-Based Methods
• Addressing Cold Start
• Usage of Dimension Reduction techniques

At the end of this topic, you will learn how to ensure the rack placement, slotting fee, marketing & distribution fee. Increase the purchases by offering bundling fees & the discount strategies will be discussed. How to analytically determine the products getting sold together will help strategize the increase in sales. It will be a blend of theoretical concepts & usage of R programming to accomplish this practically.

Tools

• Introduction to Association Rules
• Emergence of Data – POS
• Strategies & Applications of Association Rules
• Apriori Algorithm
• Performance Measures
  • Support
  • Confidence
  • Life Ratio
• Innovative Applications
• Sequential Pattern Mining

At the end of this topic, you will learn how to effectively use the travel routes by the logistics firms to ensure that the goods are transported faster. How many warehouses should be placed & at what distance & at what locations to be most profitable? Also, this can be extended to the use of social media to improve brand awareness. It will be a blend of theoretical concepts & usage of NodeXL to accomplish this practically.

• Graph/Network, Vertices/Nodes & Edges/Links
• Network Characterization
  • Node properties (Degree, Closeness, Eigenvector, Betweenness, Page Rank, Egocentric)
  • Edge properties (How to weigh)
  • Network properties (Path, Shortest path, Diameter, Cluster coefficient)
• Link Prediction
• Entity Resolution
• Fast Greedy
• Leading Eigenvector

At the end of this topic, you will learn how to deal with unstructured textual data. You will be able to generate word clouds & also perform sentiment analysis to draw meaningful insights. You will be able to perform analysis on social media data (Twitter) by extracting the tweets using R. You will be able to extract topics for performing Natural Language Processing. It will be a blend of theoretical concepts & usage of R to accomplish this practically.

• Introduction to Text Analysis
  • Tokenization procedures
  • Simple Bag-of-words (BOW) representation
  • Term-Document Matrix structures
  • Basic display aids
  • Sentiment Analysis
  • What and Why
  • Sentiment scoring schemes
  • Tidytext introduction
  • Clustering BOW structures
• Intro to NLP using OpenNLP
  • Annotations, POS tagging, NER, Chunking, etc.
• Customizing Chunking – Homebrewed
• A Quick look at CoreNLP capabilities
• Latent Semantic Analysis
• GloVe and Linguistic Regularities
• Wordnet explorations

At the end of this topic, you will learn how to track the various metrics such as the number of people visiting the website, time spent on each page or product, navigation path followed by user leading to sales. You will learn about how to use linear regression in understanding about increasing paid ads performance. Also, you will learn about the various keywords used in contemporary customer analytics. It will be a blend of theoretical concepts & usage of Google Analytics & R to accomplish this practically.

• Introduction to Google Analytics
• Install Tracking Tag, Create Views & Adding Filters
• Understanding Reports, Metric & Dimensions
• Interact with Graphs
• Segmentation, Basic Filters
• Audience Demographics, Reports & Interests
• Use of Behavior Report & Technology Report
• Acquisition Reports by Channels, Sources & Mediums
• Social Report & Network Referrals
• Measuring Value of Social with Conversions
• Behavior, Site Content Reports
• Track Events & Real-time Data
• Integrate with BigQuery & R
• Cohort Analysis & Filters
• Advanced Google Analytics
• Search Engine Advertising Analytics
• Sponsored Search Advertising
• Linear Regression for Enhancing Advertisement Position & thereby Profits
• Modeling Click-Through Rates

At the end of this topic, you will learn how to keep your customers engaged with the utmost satisfaction. Learn how to address frequently asked questions with the latest information pulled out from the database. You will learn how revenue increases by the application of Chatbots. Understand how the context can be addressed using NLP concepts, using voice to text and text to voice models.

• Chatbots in Retail
• Introduction to Conversational Chatbots
• Building Block of Chatbot: Intents & Entities
• Taking actions based on Context using NLP
• Chatbot Deployment

At the end of this topic, you will learn how to keep the unstructured data using Deep Learning concepts. Learn how machines (computers) see an Image or a Video input using Computer Vision. Process the images and videos using CNN to develop AI applications in capturing the customers' purchasing behavior. Face recognition systems to identify a repeat customer from a new customer.

• Video Analytics for Customer Behavior Analysis in Retail
• Introduction to unstructured data generated in Retail
• Processing Videos using Computer Vision & OpenCV
• Convolution Neural Network & its Architecture
• Image processing using CNN
• Filters
• Feature Maps
• Pooling Layers
• Downsampling