Author

Aybike Akici

Degree Name

Master of Science (MS)

Date of Award

10-2018

Degree Level

M.S.

LCSH subject

Box-Jenkins forecasting

Identifier

ETD2018Akici

School/University

St. Mary's University (San Antonio, Texas)

Document Type

Thesis

First Advisor

Moras, Rafael

Abstract

We describe a fully empirical study on demand forecasting, that is applicable to any real-world data. This is a hands-on case study on the power of social media in demand forecasting. We implement a Box-Jenkins methodology with exogenous variables, namely ARIMAX, to forecast Walmart's future sales. The social media components that we utilize are the number of likes and comments on the official Facebook page of Walmart. The details of the empirical investigation for fitting the best ARIMAX model are presented, and the results are discussed. With this thesis, we demonstrate that social media information should be considered in forecasting, as it is very valuable for any company when performing demand planning, and inventory management.

Creative Commons License

Creative Commons Attribution-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-No Derivative Works 4.0 License.

Included in

Engineering Commons

Share

COinS