Revolutionizing Demand Sales Forecasting: A Novel Approach through Ensemble of Statistical Time Series and Machine Learning Techniques

Myneni, Jyothirmai (2023) Revolutionizing Demand Sales Forecasting: A Novel Approach through Ensemble of Statistical Time Series and Machine Learning Techniques. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (576kB) | Preview

Abstract

Companies in today's fast-paced market have an immediate need to accurately foresee their future prospects due to the volatility of prices brought on by variables like inflation, economic conditions, and client demands. To get over this problem, we implemented a strategy for sales demand forecasting based on time series concepts. We test and contrast a variety of different Time-Series models to find the one that is most effective at forecasting future sales based on consumers' requirements and wants. Random Forest, Linear Regression, Decision Tree, Support Vector Machine (SVM), Gradient Boosting Regression, LSTM, and ANN are just few of the machine learning models we use in our research. ARIMA and Prophet are two examples of classic time series models. Measures of error like as Mean Squared Error, Mean Absolute Error, and Mean Absolute Percentage Error are used to evaluate the quality of each model. Our goal is to find the best model for Time-Series analysis, and we want to achieve so by conducting a thorough examination. Informed by such accurate forecasts of future business possibilities, companies may then make investment decisions that are in line with the needs of their target demographic. Our findings will allow businesses to anticipate and adapt to changing market conditions, allowing them to maximise their returns on investment.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Milosavljevic, Vladimir UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HB Economic Theory > Business Cycles. Economic Fluctuations Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	29 Nov 2024 15:51
Last Modified:	29 Nov 2024 15:51
URI:	https://norma.ncirl.ie/id/eprint/7217

Actions (login required)

View Item