TIME SERIES MODELS AND BUSINESS FORECASTING

Paper Code: 
24MBB325
Credits: 
4
Contact Hours: 
60.00
Max. Marks: 
100.00
Objective: 

The course will enable students to understand and apply time series analysis techniques, including ARIMA and volatility models, to forecast and manage data in various contexts, with an emphasis on multivariate time series and appropriate forecasting methods.

Course Outcomes: 

Course

Learning outcome

(at course level)

Learning and teaching

strategies

Assessment Strategies

Course Code

Course title

24MBB325

Time Series Models And Business Forecasting

(Practical)

 

CO388: Analyze time    series                         based

business data.

CO389: Apply ARIMA modeling of stationary and non-stationary time series.

CO390: Identify frequently used volatility models and inspect the problems arising when analyzing unit root processes.

CO391: Identify and select testing strategy for volatility models.

CO392: Apply analytics on real world time series and forecast results.

CO393: Contribute effectively in course-specific interaction

Approach in teaching: Interactive Lectures, Group Discussion, Tutorials, Case Study

 

Learning activities for the students: Self-learning assignments, presentations

Class test, Semester endexaminations, Quiz, Assignments, Presentation

 

12.00
Unit I: 
Basic concepts in time series analysis

Stationarity, autocovariance, autocorrelation, partial autocorrelation, Exploring Time series data patterns, Types of forecasting Techniques and choosing the appropriate method of forecasting

 

12.00
Unit II: 
ARIMA modelling

Autoregressive models, moving average models, smoothing Technques, duality, model properties, parameter estimates, forecasts, Applications in Management

 

12.00
Unit III: 
Volatility models

ARCH and GARCH modelling, testing strategy for heteroscedastic models, volatility forecasts, Forecasting errors, choosing the best methbod

 

12.00
Unit IV: 
Integrated processes

Difference stationarity, testing for unit roots, spurious correlation and Managing the forecasting process.

 

12.00
Unit V: 
Multivariate time series

Time series regression, VAR models, cointegration, forecasting properties

 

 

 

Essential Readings: 
  • Mark J. Bennett, Dirk L. Hugen, Financial Analytics with R, Cambridge University Press
  • John E Hanke, Dean W. Wichern, Business Forecasting, PHI Publications

 

References: 

Suggested readings

  • George E. P. Box, Gwilym M. Jenkins, Gregory C. Reinsel, Greta M. Ljung, (2017) Time Series Analysis: Forecasting and Control, Wiley, 5th Edition
  • Aileen Nielsen (2019), Practical Time Series Analysis: Prediction with Statistics and Machine Learning, O'Reilly

E-RESOURCES RECOMMENDED:

JOURNALS:

 

 

Academic Year: 
2024-2025
  • Printer-friendly version
  • PDF version