Course Catalog 
Resources 
Shareable Certificate
Earn a sharable certificate upon completion
Retail and Consumer Goods Analytics
This learning track introduces the concepts, techniques, and applications of Data Treatment, Data Visualizations, Feature Engineering, Descriptive and Predictive Analysis, Supervised and Unsupervised Machine Learning, ML Model Development, Hyperparameter tuning, Evaluation and Selection, Ensemble Learning, Explainable AI methods in the Retail and Consumer Goods industry.
-
30 Courses
-
26 Projects & Case Studies
-
Difficulty: Intermediate
Foundational education or some experience is recommended
-
Duration: Approximately 3 months
Suggested learning pace is 5hr/week
Course Overview
- Understanding of the concepts and various techniques of Supervised Machine Learning, Unsupervised Machine Learning and Ensemble Learning focussing on building an ML model, Hyperparameter optimization, Model Evaluation and Selection to fulfil various objectives like customer segmentation, forecasting of product price, sales etc.
- Learn various Data Management and Data Transformation techniques to fetch data from different tables and convert them to useable format and basics of Data Visualization, Univariate & Multivariate data analysis to gain insights on product sales, customer purchase behaviour etc.
- Develop a thorough understanding of Text analytics, and its application in sentiment analysis of customer reviews of products.
- Learn how to apply Explainable AI methods like LIME and SHAP to deeply understand the model predictions and perform efficient model selection for further use in real-world problems in the CPG and Retail industry.
What’s included
Lifetime Access
Access this case study for life once completed
Flexible Scheduling
Start learning online immediately, at your own pace
Desktop Only
We recommend completing this learning track on a desktop
Skills You Will Learn
- Fundamentals of Data Analytics
- Fundamentals of Data Preprocessing
- Data Mining Concepts and Techniques
- Basic Data Visualization Methods- I
- Advanced Feature Engineering techniques
- Machine Learning – Linear Regression
- Model Evaluation Techniques – Regression Models
- Model Selection Techniques
- Machine Learning – Logistic Regression
- Model Evaluation Techniques – Classification Models
- Basics of Hyperparameter Tuning – Linear & Logistic Regression
- Getting Started with Naive Bayes Classifier
- Support Vector Machines in ML
- Hyperparameter Tuning in SVM
- Understanding Decision Trees
- Hyperparameter Tuning in Tree-Based Models
- Bagging & Random Forest in Machine learning
- Introduction to Gradient Boosting Classification
- Introduction to Extreme Gradient Boosting Classifier
- Introduction to AdaBoost Classifier
- Concepts and Application of Objective and Subjective Segmentation
- Understanding Principal Component Analysis (PCA)Fundamentals of Time Series Analysis
- Introduction to Natural Language Processing (NLP)Mining Text Data Cleansing, Treatment, Structural Representation & Visualization
- Text Analytics – Classification and Clustering
- Sentiment Analysis – Using Unstructured Text Data
- Introduction to Explainable AI (XAI) using LIME
- Introduction to Explainable AI (XAI) using SHAP
- Introduction to Explainable AI (XAI) for Text using LIME & SHAP
- Sales Insights using Statistical Analysis for a Shoe Retail Store
- Measuring Online Customer Loyalty – Application of RFM (Recency, Frequency, Monetary)Customer Segmentation for e-Commerce retailer
- Analyzing and Predicting the Laptop prices for an Online Retail Store
- Applying Linear Regression to predict used car prices
- Assumptions in OLS Regression Models (Ordinary Least Squares)Predict Holiday Sales for A Retail Client – Application of Linear Regression
- Predict Credit Card Customer Attrition – Application of Logistic Regression
- Predict Customer Attrition Using Naïve Bayes Classification
- Identify Customers with Higher Likelihood of Credit Card Attrition – Application of Decision Tree
- Customer Churn Prediction for a Telecom Client
- Browsing or Purchasing: Prediction of Online Shoppers Purchasing Intentions
- Estimating Price for Diamonds – Supervised Learning -Hyperparameter Optimization
- Customer Segmentation in Retail – Application of K-Means Clustering Algorithm
- Segmentation on Conversion of Insurance Leads
- Forecasting Vehicle Registration for Sales Trends on Monthly basis
- Demand Forecasting for a Global Retail Company
- Monthly demand forecasting in retail industry
- Forecasting Pharma Product Sales
- Application of Text Classification on Women’s E-Commerce Clothing Reviews
- Sentiment Analysis on Car Reviews
- Customer Sentiment analysis for an e-commerce retailer
- Customer Sentiment Analysis in Insurance claims processing
- Application of Various Text Clustering Techniques on Customer Feedback Data
- Predicting Car Price using XAI
- Analyzing House Sales Using XAI
How it Works
Learn new skills that will boost your career by enrolling in courses across data analytics, data science, ML and AI. These courses will utilize readings, videos, quizzes, data cases, and even coding exercises to teach you skills and concepts in a way that will solidify your new knowledge for hands-on application.
With our hands-on projects, you will take your newly learned skills along with our 750+ low-code/no-code functions and embedded coding console to complete milestone-based projects. Once completed, you will have effectively applied new skills and concepts to real-world data cases that can be translated directly into your career.
Complete assessments and track your progress in real-time to benchmark your proficiency in relation to key functional areas. As you progress through your courses, our patented platform will utilize ML and AI to record and analyze your inputs and output to provide active feedback and recommendations that will help you learn more effectively than the standard Letter Grade system used today.
Learner Outcomes
Complete learning tracks to earn shareable certificates and badges. These awarded items will look great in your portfolio as you showcase your skills, projects, and experience to employers and colleagues.
- Application of Descriptive Analysis and Visualization to analyze problems related to Sales Insights, Measuring Customer Loyalty, and Laptop Pricing.
- Application of various Supervised Learning techniques like Regression & Classification models to make predictions for Holiday sales, credit card customer attrition,identification of potential customers among online browsers and customer churn.
- Application of various Unsupervised Learning techniques like Clustering algorithms done to group customers with similar traits to assist in targeted marketing campaigns.
- Application of Time Series & Text Analytics to solve problems related to Product sales, Demand Forecast, and Sentiment Analysis in Insurance Claims
“Rolai provides contextual upskilling opportunities … on one single platform.”
“An excellent tool for anyone who wants to quickly learn the ropes.”
“Rolai is the best program available for someone looking to enhance their skills”
“Great way to learn data analytics and data science”
“The courses were excellent and covered topics that I didn’t expect”
Rolai’s patented process provides a personalized learning process for each user. Rolai goes deeper than simply learning concepts and testing your skills. At Rolai, learners can apply their skills to actual industry use cases and projects.
Our courses include readings, videos, quizzes, and hands-on data cases that are completed using our virtual lab; give learners an applied learning experience.
No additional tools are needed to begin learning with Rolai. Our virtual lab contains the necessary data workspace and an embedded coding console.
- We have internal SMEs across industries and domains that we work with to develop relevant content and assure quality datasets and problem statements.
- We also work with enterprises and universities to develop new content directed towards their industry and expertise.
