Demand Forecasting in Python: Deep Learning Model Based on LSTM Architecture versus Statistical Models

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27510%2F21%3A10247955" target="_blank" >RIV/61989100:27510/21:10247955 - isvavai.cz</a>

Result on the web

<a href="http://acta.uni-obuda.hu/Kolkova_Navratil_115.pdf" target="_blank" >http://acta.uni-obuda.hu/Kolkova_Navratil_115.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.12700/APH.18.8.2021.8.7" target="_blank" >10.12700/APH.18.8.2021.8.7</a>

Result language

angličtina

Original language name

Demand Forecasting in Python: Deep Learning Model Based on LSTM Architecture versus Statistical Models

Original language description

Demand forecasting for business practice is one of the biggest challenges of current business research. However, the discussion on the use of forecasting methods in business is still at the beginning. Forecasting methods are becoming more accurate. Accuracy is often the only criterion for forecasting. In the reality of business practice or management is also influenced by other factors such as runtime, computing demand, but also the knowledge of the manager. The goal of this article is to verify the possibilities demand forecasting using deep learning and statistical methods. Suitable methods are determined on based multi-criteria evaluation. Accuracy according to MSE and MAE, runtime and computing demand and knowledge requirements of the manager were chosen as the criteria. This study used univariate data from an e-commerce entity. It was realized 90-days and 365-days demand forecasting. Statistical methods Seasonal naive, TBATS, Facebook Prophet and SARIMA was used. These models will be compared with a deep learning model based on recurrent neural network with Long short-term memory (LSTM) layer architecture. The Python code used in all experiments and data is available on GitHub (https://github.com/mrnavrc/demand_forecasting). The results show that all selected methods surpassed the benchmark in their accuracy. However, the differences in the other criteria were large. Models based on deep learning have proven to be the worst on runtime and computing demand. Therefore, they cannot be recommended for business practice. As a best practice model has proven Prophet model developed at Facebook.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

50206 - Finance

Project

<a href="/en/project/GA18-13951S" target="_blank" >GA18-13951S: New approaches to financial time series modelling based on soft computing</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2021

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Acta Polytechnica Hungarica

ISSN

1785-8860

e-ISSN

—

Volume of the periodical

18

Issue of the periodical within the volume

8

Country of publishing house

HU - HUNGARY

Number of pages

19

Pages from-to

123-141

UT code for WoS article

000697928900007

EID of the result in the Scopus database

2-s2.0-85117762084