How to Learn from Others: Transfer Machine Learning with Additive Regression Models to Improve Sales Forecasting

被引:1
|
作者
Hirt, Robin [1 ]
Kuehl, Niklas [1 ]
Peker, Yusuf [1 ]
Sauger, Gerhard [1 ]
机构
[1] Karlsruhe Inst Technol KIT, Karlsruhe, Germany
来源
2020 IEEE 22ND CONFERENCE ON BUSINESS INFORMATICS (CBI 2020), VOL I - RESEARCH PAPERS | 2020年
关键词
Machine learning; Transfer Learning; Sales Forecasting; NEURAL-NETWORK; BIG DATA; ARIMA;
D O I
10.1109/CBI49978.2020.00010
中图分类号
F [经济];
学科分类号
02 ;
摘要
In a variety of business situations, the introduction or improvement of machine learning approaches is impaired as these cannot draw on existing analytical models. However, in many cases similar problems may have already been solved elsewhere-but the accumulated analytical knowledge cannot be tapped to solve a new problem, e.g., because of privacy barriers. For the particular purpose of sales forecasting for similar entities, we propose a transfer machine learning approach based on additive regression models that lets new entities benefit from models of existing entities. We evaluate the approach on a rich, multi-year dataset of multiple restaurant branches. We differentiate the options to simply transfer models from one branch to another ("zero shot") or to transfer and adapt them. We analyze feasibility and performance against several forecasting benchmarks. The results show the potential of the approach to exploit the collectively available analytical knowledge. Thus, we contribute an approach that is generalizable beyond sales forecasting and the specific use case in particular. In addition, we demonstrate its feasibility for a typical use case as well as the potential for improving forecasting quality. These results should inform academia, as they help to leverage knowledge across various entities, and have immediate practical application in industry.
引用
收藏
页码:20 / 29
页数:10
相关论文
共 41 条
  • [1] Machine-Learning Models for Sales Time Series Forecasting
    Pavlyshenko, Bohdan M.
    DATA, 2019, 4 (01)
  • [2] A review and analysis of regression and machine learning models on commercial building electricity load forecasting
    Yildiz, B.
    Bilbao, J. I.
    Sproul, A. B.
    RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2017, 73 : 1104 - 1122
  • [3] Inverting the fundamental diagram and forecasting boundary conditions: how machine learning can improve macroscopic models for traffic flow
    Briani, Maya
    Cristiani, Emiliano
    Onofri, Elia
    ADVANCES IN COMPUTATIONAL MATHEMATICS, 2024, 50 (06)
  • [4] Modelling and forecasting new cases of Covid-19 in Nigeria: Comparison of regression, ARIMA and machine learning models
    Busari, S. I.
    Samson, T. K.
    SCIENTIFIC AFRICAN, 2022, 18
  • [5] Using Congestion to Improve Short-Term Velocity Forecasting with Machine Learning Models
    Lira, Cristian
    Araya, Aldo
    Vejar, Bastian
    Ordonez, Fernando
    Rios, Sebastian
    CYBERNETICS AND SYSTEMS, 2024, 55 (06) : 1378 - 1398
  • [6] How Well Can Machine Learning Models Perform without Hydrologists? Application of Rational Feature Selection to Improve Hydrological Forecasting
    Moreido, Vsevolod
    Gartsman, Boris
    Solomatine, Dimitri P.
    Suchilina, Zoya
    WATER, 2021, 13 (12)
  • [7] Do the robot: Lessons from machine learning to improve conflict forecasting
    Colaresi, Michael
    Mahmood, Zuhaib
    JOURNAL OF PEACE RESEARCH, 2017, 54 (02) : 193 - 214
  • [8] Transformational machine learning: Learning how to learn from many related scientific problems
    Olier, Ivan
    Orhobor, Oghenejokpeme, I
    Dash, Tirtharaj
    Davis, Andy M.
    Soldatova, Larisa N.
    Vanschoren, Joaquin
    King, Ross D.
    PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2021, 118 (49)
  • [9] Ridge regression ensemble of machine learning models applied to solar and wind forecasting in Brazil and Spain
    Carneiro, Tatiane C.
    Rocha, Paulo A. C.
    Carvalho, Paulo C. M.
    Fernandez-Ramirez, Luis M.
    APPLIED ENERGY, 2022, 314
  • [10] Forecasting geothermal temperature in western Yemen with Bayesian-optimized machine learning regression models
    Al-Fakih, Abdulrahman
    Al-khudafi, Abbas
    Koeshidayatullah, Ardiansyah
    Kaka, Sanlinn
    Al-Gathe, Abdelrigeeb
    GEOTHERMAL ENERGY, 2025, 13 (01):