Walmart Sales forecasting using Equilibrium optimized Deep LSTM

Perumal, Arul Selvam (2023) Walmart Sales forecasting using Equilibrium optimized Deep LSTM. Masters thesis, Dublin, National College of Ireland.

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

Abstract

For sales prediction, timely prediction presents accurate information for companies when business trends are constantly developing in order to attain a strong balance between demand and supply. Sales forecasting is formulated as a time series forecasting issue that aspires to forecast the volume of future sales for diverse products with the observation of several significant parameters for instance, season, discount, brand, and so on., corresponding to historical sales records. Moreover, in order to carry out accurate sales forecasting, this research work intends to perform Walmart sales prediction using Equilibrium Optimizer (EO)-deep Long Short Term Memory (deep LSTM), called the EO-deep LSTM model. Initially, the input data is pre-processed using missing data imputation and data augmentation is done using min-max normalization. Then, technical indicators, namely Simple Moving Average (SMA), Volume Adjusted Moving Average (VAMA), Average Directional Movement Index (ADX), Weighted Moving Average (WMA), Trend Detection Index (TDI), and Exponential Moving Average (EMA) are extracted. With these indicators as features, the prediction is done using the Deep LSTM model, which is trained using an EO algorithm. The experimentation is carried out using Walmart sales forecasting dataset and the performance of the proposed approach is evaluated by parameters, like Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE).

Item Type:	Thesis (Masters)
Supervisors:	Name Email Staikopoulos, Athanasios UNSPECIFIED
Uncontrolled Keywords:	sales prediction; Walmart; pre-processing; data augmentation; deep LSTM
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Retail Industry
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	28 Dec 2024 14:36
Last Modified:	28 Dec 2024 14:36
URI:	https://norma.ncirl.ie/id/eprint/7249

Actions (login required)

View Item