Research on Sales Forecasting of New Energy Vehicles Based on Interbrand and SARIMA-BP Neural Network

Ruiqi Luo

2025

Abstract

With the rapid development of the new energy vehicle market, accurate sales forecasting is crucial for industry decision-making. This study proposes a forecasting method that combines the Interbrand model with the Seasonal Autoregressive Integrated Moving Average - Back Propagation Neural Network (SARIMA-BP neural network) to quantify brand influence and improve forecasting accuracy. Firstly, based on the improved Interbrand model, the brand value of new energy vehicles is quantified from financial dimensions (new energy business revenue, average vehicle price) and brand strength (segment market share, R&D investment, search index) to solve the problem of data separation difficulties in traditional models. Secondly, a SARIMA-BP neural network fusion model is constructed. SARIMA is used to process the linear and seasonal characteristics of the sales time series, and the BP neural network is used to fit the nonlinear part, and brand influence is introduced as the key independent variable. The empirical analysis uses 48 sets of monthly data from BYD, Tesla, Li Auto, and NIO from 2021 to 2024 as samples. The results show that the fusion model is significantly better than the single SARIMA model and the combined model that does not incorporate brand value in terms of Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE), verifying the key role of brand influence in sales forecasting. This research provides a new method for forecasting new energy vehicle sales that takes into account both brand effects and data characteristics, and has reference value for corporate market strategy formulation.

Paper Citation

in Harvard Style

Luo R. (2025). Research on Sales Forecasting of New Energy Vehicles Based on Interbrand and SARIMA-BP Neural Network. In Proceedings of the 2nd International Conference on Innovations in Applied Mathematics, Physics, and Astronomy - Volume 1: IAMPA; ISBN 978-989-758-774-0, SciTePress, pages 397-401. DOI: 10.5220/0013826600004708

in Bibtex Style

@conference{iampa25,
author={Ruiqi Luo},
title={Research on Sales Forecasting of New Energy Vehicles Based on Interbrand and SARIMA-BP Neural Network},
booktitle={Proceedings of the 2nd International Conference on Innovations in Applied Mathematics, Physics, and Astronomy - Volume 1: IAMPA},
year={2025},
pages={397-401},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013826600004708},
isbn={978-989-758-774-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Innovations in Applied Mathematics, Physics, and Astronomy - Volume 1: IAMPA
TI - Research on Sales Forecasting of New Energy Vehicles Based on Interbrand and SARIMA-BP Neural Network
SN - 978-989-758-774-0
AU - Luo R.
PY - 2025
SP - 397
EP - 401
DO - 10.5220/0013826600004708
PB - SciTePress