Course

Introduction and Overview of the Predictive Analytics – Building a Predictive Model – Predictive Power and Overfitting – Data Partitioning – Exploratory Data Analysis – Data Visualization – Dimension Reduction – Principal Components Analysis – Performance Evaluation – Evaluating Predictive Performance – Judging Classifier Performance – Lift and Decile Charts – Oversampling.

Prediction and Classification Methods – Multiple Linear Regression – Explanatory vs. Predictive Modeling – Estimating the Regression Equation and Prediction – The k-NN Classifier (Categorical Outcome) – The Naive Bayes Classifier – Classification and Regression Trees – Logistic Regression – Neural Nets – Discriminant Analysis – Combining Methods: Ensembles – Uplift Modeling – Association Rules and Collaborative Filtering – Clustering.

Forecasting Time Series – Components of a Time Series – Data Partitioning and Performance Evaluation for Time Series – Naive Forecasts – Smoothing Methods – Introduction – Moving Average – Simple Exponential Smoothing – Advanced Exponential Smoothing–Regression-Based Forecasting – Autocorrelation and ARIMA Models – Data Analytics – Social Network Analytics – – Text Mining – predictive analytics in business application – Other Case Studies.

Preamble

Predictive analytics is used to predict of future outcomes based on historical data using statistical and machine learning techniques. This course provides a comprehensive review of various analytics methods. Students will gain an in-depth understanding of supervised and unsupervised learning for predictive analytics. The course will also cover the principles of forecasting analytics.

Course Objectives

• To familiarize students with the methods for exploration and visualization of data
• To develop machine learning models for predictive tasks
• To choose suitable performance measures for predictive models
• To apply predictive modelling techniques in real world data

Course Outcomes

Prerequisites

• Linear Algebra and Probability

CO-PO Mapping

Evaluation Pattern – 70:30

• Midterm Exam – 30%
• Continuous Evaluation – 40%
• End Semester Exam – 30%

Text Book / References

1. Max Kuhn and Kjell Johnson, “Applied Predictive Modeling”, Springer, 2018.
2. Galit Shmueli, Peter Gedeck, Peter C. Bruce, Nitin R. Patel, “Data Mining for Business Analytics: Concepts, Techniques, and Applications in Python”, Wiley, 2019.
3. Daniel T. Larose and Chantal D. Larose, “Data Mining and Predictive Analytics” (Wiley Series on Methods and Applications in Data Mining), Wiley, 2015.
4. Ratner Bruce, ”Statistical and Machine-Learning Data Mining:: Techniques for Better Predictive Modeling and Analysis of Big Data”, CRC Press, 2017.
5. Abbott Dean, ”Applied predictive analytics: Principles and techniques for the professional data analyst”, John Wiley & Sons, 2014.