Advanced Furniture Sales Forecasting Using Machine Learning and Deep Learning Techniques

Download

Volume 5 Issue 2 2024

Author(s):

Usman Amjad NED University of Engineering and Technology, Karachi, Pakistan , usmanamjad@neduet.edu.pk

Samar Raza Talpur Sukkur IBA University,Pakistan, samartalpur@iba-suk.edu.pk

Saad Ahmed Iqra University, Karachi, Pakistan, Saad.ahmed@iqra.edu.pk

Hira Farman Iqra University, Karachi, Pakistan, hira.farman@iqra.edu.pk

Umm e Laila Institute of Business Management, Karachi, Pakistan, umme.laila@iobm.edu.pk

Abstract Accurate sales forecasting in the furniture industry plays a vital role in maintaining optimal inventory levels and enhancing profitability. While underproduction limits revenue generation, overproduction leads to financial losses due to excess inventory. The objective of this study is to improve the accuracy of sales forecasting, align production with demand, and optimize inventory management in order to enhance profit margins within the furniture industry. To achieve this, historical sales data spanning from 2014 to 2023 was utilized, and various machine learning and deep learning models were evaluated. The results revealed that the linear regression model outperformed all other machine learning models, achieving the highest accuracy with an R-squared score of 1.0 and the lowest error metrics, including a mean squared error of 0.001331 and a mean absolute error of 0.000849. Among the deep learning models, the Long Short-Term Memory model delivered the best performance, achieving an R-squared value of 0.737649, significantly outperforming the standard Recurrent Neural Network, which achieved an R-squared value of only 0.131056. These findings demonstrate the effectiveness of linear regression for short-term predictions and the capability of long short-term memory models in capturing sequential patterns in sales data. Both models present valuable tools for improving inventory management and production planning in the furniture industry.
Keywords Furniture, sales forecasting, Machine Learning Models, Linear Regression, Random Forest and Decision Tree, deep learning
Year 2024
Volume 5
Issue 2
Type Research paper, manuscript, article
Recognized by Higher Education Commission of Pakistan, HEC
Category
Journal Name ILMA Journal of Technology & Software Management
Publisher Name ILMA University
Jel Classification --
DOI -
ISSN no (E, Electronic) 2790-590X
ISSN no (P, Print) 2709-2240
Country Pakistan
City Karachi
Institution Type University
Journal Type Open Access
Manuscript Processing Blind Peer Reviewed
Format PDF
Paper Link https://ijtsm.ilmauniversity.edu.pk/arc/Vol5/i2/pdf2.pdf
Page 11-25