School of Inspired Leadership
Predictive Analytics
Faculty: Dr. D. Das Program: BLP
Phone: +919811535749 Contact Hours: 24 hrs
Email:
[email protected] Sessions: 16
COURSE DESCRIPTION
Predictive analytics turns data into valuable, actionable information. Predictive analytics uses data to
determine the probable future outcome of an event or a likelihood of a situation occurring. Predictive
analytics encompasses a variety of statistical techniques from modelling, machine learning, and data
mining that analyse current and historical facts to make predictions about future events. In business,
predictive models exploit patterns found in historical and transactional data to identify risks and
opportunities. Almost all management reporting such as sales, marketing, operations, hr and finance, uses
this type of analysis for futuristic decisions.
LEARNING OUTCOMES
From this course the students would be able to
Process data (using integration, cleaning and transformation) for visualization, modeling and
interpretation.
Create predictive models using statistical, mathematical, data mining and machine learning
techniques, and evaluate and interpret such models to support fact-based decision making.
Work both independently and in a team to solve large data analysis projects.
Clearly communicate and present complex analytics results to business clients, using practical and
simple business terms that can be understood by a general non-technical audience.
Identify and evaluate appropriate data analytics techniques to be used depending on the specific
information needs of the project.
Use data visualization tools to communicate predictive modelling results in an effective way.
READING MATERIAL
Reference Books
Seema Acharya, Data Analytics using R, Mc Graw Hill
John E. Hanke, Dean W. Wichern and Arthur G. Reitsch, “Business Forecasting”, Pearson
Education Asia, Eighth Edition
Spyros Makridakis, Steven C. Wheelwright and Rob J. Hyndman, “Forecasting Methods and
Applications”, John Wiley & Sons, Inc., Third Edition
D. N. Gujarati and Sangeetha, Basic Econometrics, McGraw-Hill, Fourth Edition
George E. P. Box, Gwilym M. Jenkins and Gregory C. Reinsel, “Time Series Analysis”, Pearson
Education, Third Edition
PEDAGOGY & EVALUATION
Name of the Course Term BRM 1st 1
The course consists of lectures, case studies and computer application. The focus of the course will be
applying concepts and ideas to real-world problems—both in case discussions and also in companies and
work situations. The success of the course in terms of individual and collective learning depends upon the
input into class discussion. This requires adequate prior preparation for class and willingness to take
responsibility for the quality and constructiveness of class discussion.
Grades will be based on class contribution, team project and in-class assignments/quiz. Breakup of the
grade for this course is as follows:
Class Participation & Attendance 10%
Quiz/Class Assignments 10%
Term Project 1 40%
End Term Exam 40%
GRADING
Students are graded on the 5 point scale below. If a student does not meet the minimum requirements to
earn the lowest grade, the faculty may choose not to grade him/her. Each student shall be graded on the
following 5 point scale and the required expectations at each level are as follows:
Novice: Knowledge of basic concepts of the subject
Beginner: Understanding and identifying the business problem by looking the data in hand.
Competent: Application of predictive tools and techniques to generate outputs
Accomplished: Showcasing the ability to analyse these outputs
Role Model: Ability to prepare business report in an efficient presentable manner
TERM PROJECT
Students will work in their pre-determined groups on the project that involves any business data of a
company. Data would be gathered from secondary sources. Students are expected to apply predictive
technique for forecasting future outcomes. This will give you an opportunity to apply these concepts in
the context of finding solutions to practical problem faced by organizations. Finally make a presentation
for the report in the last class.
SESSION PLAN (please note session plan may change if needed).
SESSION SESSIONS READINGS/CASES
SESSION 1 Prediction Prospective, Data Patterns
SESSION 2 Exploratory Data Analysis
SESSION 3 Exploratory Data Analysis
SESSION 4 Predictive Models and Accuracy
SESSION 5 Marginal and Exponential Naïve Employee Forecasting
SESSION 6 Trend and Auto Regression Employee Forecasting
SESSION 7 Exponential Smoothing: Holt’s Air Passenger
SESSION 8 Seasonal Naïve Beer Production
SESSION 9 Seasonal and Auto Regression Electricity Consumption
SESSION 10 Exponential Smoothing: Winter’s Beer Production
Name of the Course Term BRM 1st 2
SESSION 11 Decomposition & Moving Average Sales Forecasting
SESSION 12 Diffusion Model: Logistics Mobile Phone Subscriber
SESSION 13 Diffusion Model: Gompertz Car Ownership
SESSION 14 Autoregressive Integrated Moving Exchange Rate
Average Model
SESSION 15 Probabilistic Forecasting: Logits Loan Defaulter
SESSION 16 Market Share: Markov Chain Murphy’s Foodliner and Ashley’s
Supermarket
Name of the Course Term BRM 1st 3
