Wildlife population prediction is critical for conservation efforts as illegal wildlife trade and habitat loss continue to threaten global biodiversity, particularly for species like African elephants. Current research faces challenges in long-term forecasting due to data limitations and uncertainty. This study aims to forecast the population trends of endangered species over the next five years and specifically predict changes in African elephant numbers to provide insights for targeted conservation strategies. In this study, collect data from international statistical websites firstly, then establish ARIMA model to predict the change of the number of endangered animal species in the next five years, using Grey forecast model to predict the number of African elephants. The data in this paper suggest that the number of endangered species is increasing by about 5%, while the remaining number of African elephants fluctuates around 250,000, showing a downward trend in next five years. This study demonstrates the importance of time series models in wildlife population prediction. The findings provide a scientific basis for formulating targeted conservation policies, especially for African elephants. Future research should incorporate spatial distribution and environmental factors of different animals to enhance predictive accuracy. We should try our best to support practical conservation projects.

Leyi Huang. Wildlife Population Prediction Based on Time Series Models. Academic Journal of Computing & Information Science(2025), Vol. 8, Issue 3: 103-108. https://doi.org/10.25236/AJCIS.2025.080314.

[1] Zhang, G. Peter. "Time series forecasting using a hybrid ARIMA and neural network model" [J]. Neurocomputing, 2003, 50: 159-175.

[2] Lim, Bryan, et al. "Time-series forecasting with deep learning: a survey" [J]. Philosophical Transactions of the Royal Society A, 2021, 379(2194): 20200209.

[3] Ospina et al. "An overview of forecast analysis with ARIMA models during the COVID-19 pandemic: Methodology and case study in Brazil" [J]. Mathematics, 2023, 11(14): 3069.

[4] Ye, Li, et al. "An enhanced multivariable dynamic time-delay discrete grey forecasting model for predicting China's carbon emissions" [J]. Energy, 2022, 249: 123681.

[5] Shumway, Robert H., et al. ARIMA models. Time series analysis and its applications: with R examples [M]. 2017: 75-163.

[6] Lee C W, Kong P. Forecasting Travel Sentiment under the Shock Effects of COVID-19 and Vaccination Using Grey Prediction Models[J]. Journal of Mathematics, 2023. DOI:10.1155/ 2023/ 7334544.