{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:31:59Z","timestamp":1781533919376,"version":"3.54.5"},"reference-count":39,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T00:00:00Z","timestamp":1778803200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["71801036"],"award-info":[{"award-number":["71801036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["71801036"],"award-info":[{"award-number":["71801036"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems"],"abstract":"<jats:p>Traffic flow prediction is an important and fundamental task for the operation of Intelligent Transportation Systems. In recent years, most studies on traffic prediction have focused on two-dimensional network traffic flow prediction, while there is still no clear consensus on the study of one-dimensional highway traffic flow prediction, for instance, regarding which model is the most appropriate. To address this gap, we conducted a systematic comparative evaluation of 27 models across five classes, including Statistical models, Machine Learning, Artificial Neural Networks, Deep Neural Networks, and Graph Neural Networks, based on five representative highway traffic datasets. To ensure fairness, evaluations were performed on raw data without signal decomposition or auxiliary modules. Surprisingly, the experimental results reveal that complex deep learning models do not demonstrate advantages in terms of conventional metrics. Instead, simple models, particularly Historical Averaging and tree-based Machine Learning models, exhibit superior performance in most scenarios. And then, we study the underlying reasons for this phenomenon from various perspectives, including the complexity of prediction tasks, the tabular data characteristics, the spectral bias of Neural Networks, and theoretical error bounds. Furthermore, we also analyze why these findings were overlooked in the previous literature, attributing the oversight to the predominant focus on signal decomposition preprocessing, inconsistent prediction settings, and the lack of comprehensive benchmarking. Supported by rich data and extensive information, this work offers valuable references and practical implications for researchers in highway traffic flow prediction. It further advocates that in the era of pursuing sophisticated models, scenario-specific analysis and appropriate simple models still deserve more attention.<\/jats:p>","DOI":"10.3390\/systems14050561","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T16:07:26Z","timestamp":1779206846000},"page":"561","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["What Is the Best Model for Highway Traffic Flow Prediction? A Large-Scale Test for Empirical Data"],"prefix":"10.3390","volume":"14","author":[{"given":"Tongkai","family":"Zhang","sequence":"first","affiliation":[{"name":"Jiangsu Key Laboratory of Urban ITS, Southeast University of China, Nanjing 210096, China"},{"name":"Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, Nanjing 210096, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng-Jie","family":"Jin","sequence":"additional","affiliation":[{"name":"Jiangsu Key Laboratory of Urban ITS, Southeast University of China, Nanjing 210096, China"},{"name":"Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, Nanjing 210096, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"Jiangsu Key Laboratory of Urban ITS, Southeast University of China, Nanjing 210096, China"},{"name":"Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, Nanjing 210096, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1061\/(ASCE)0733-947X(1995)121:3(249)","article-title":"Short-Term Prediction of Traffic Volume in Urban Arterials","volume":"121","author":"Hamed","year":"1995","journal-title":"J. Transp. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1061\/(ASCE)0733-947X(2003)129:6(664)","article-title":"Modeling and Forecasting Vehicular Traffic Flow as a Seasonal ARIMA Process: Theoretical Basis and Empirical Results","volume":"129","author":"Williams","year":"2003","journal-title":"J. Transp. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"132","DOI":"10.3141\/1644-14","article-title":"Urban Freeway Traffic Flow Prediction: Application of Seasonal Autoregressive Integrated Moving Average and Exponential Smoothing Models","volume":"1644","author":"Williams","year":"1998","journal-title":"Transp. Res. Rec."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1061\/(ASCE)0733-947X(1997)123:4(261)","article-title":"Traffic Flow Forecasting: Comparison of Modeling Approaches","volume":"123","author":"Smith","year":"1997","journal-title":"J. Transp. Eng."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1061\/(ASCE)0733-947X(1991)117:2(178)","article-title":"Nonparametric Regression and Short-Term Freeway Traffic Forecasting","volume":"117","author":"Davis","year":"1991","journal-title":"J. Transp. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1109\/TITS.2004.837813","article-title":"Travel-Time Prediction with Support Vector Regression","volume":"5","author":"Wu","year":"2004","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_9","unstructured":"Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017, January 4\u20139). LightGBM: A Highly Efficient Gradient Boosting Decision Tree. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_10","first-page":"8878011","article-title":"Traffic Prediction Using LSTM, RF and XGBoost","volume":"2021","author":"Lam","year":"2021","journal-title":"J. Adv. Transp."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2809","DOI":"10.1007\/s40996-024-01393-x","article-title":"Prediction of Traffic Flow Based on Calendar Data on Suburban Roads (Case Study: Chalus Road)","volume":"48","author":"Afandizadeh","year":"2024","journal-title":"Iran. J. Sci. Technol. Trans. Civ. Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/j.trc.2015.03.014","article-title":"Long short-term memory neural network for traffic speed prediction using remote microwave sensor data","volume":"54","author":"Ma","year":"2015","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Ma, X., Dai, Z., He, Z., Ma, J., Wang, Y., and Wang, Y. (2017). Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction. Sensors, 17.","DOI":"10.3390\/s17040818"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2191","DOI":"10.1109\/TITS.2014.2311123","article-title":"Deep Architecture for Traffic Flow Prediction: Deep Belief Networks with Multitask Learning","volume":"15","author":"Huang","year":"2014","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"114496","DOI":"10.1109\/ACCESS.2019.2935504","article-title":"Deep Temporal Convolutional Networks for Short-Term Traffic Flow Forecasting","volume":"7","author":"Zhao","year":"2019","journal-title":"IEEE Access"},{"key":"ref_16","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention Is All You Need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"616","DOI":"10.3390\/forecast5040034","article-title":"Forecasting the Traffic Flow by Using ARIMA and LSTM Models: Case of Muhima Junction","volume":"5","author":"Katambire","year":"2023","journal-title":"Forecasting"},{"key":"ref_18","first-page":"25","article-title":"Urban Traffic Flow Prediction Using LSTM and GRU","volume":"38","author":"Jang","year":"2023","journal-title":"Eng. Proc."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Chahal, A., Gulia, P., Gill, N.S., and Priyadarshini, I. (2023). A Hybrid Univariate Traffic Congestion Prediction Model for IoT-Enabled Smart City. Information, 14.","DOI":"10.3390\/info14050268"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Vo, H.H.-P., Nguyen, T.M., Bui, A.K., and Yoo, M. (2024). Traffic Flow Prediction in 5G-Enabled Intelligent Transportation Systems Using Parameter Optimization and Adaptive Model Selection. Sensors, 24.","DOI":"10.3390\/s24206529"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Shafiei, S., Zhu, Q., Qin, A.K., Mihaita, S.A., Grzybowska, H., and Dia, H. (2025). Road traffic attributes prediction using deep learning hybridization by the traffic fundamental diagram. J. Intell. Transp. Syst., 1\u20136.","DOI":"10.1080\/15472450.2025.2577735"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1061\/(ASCE)0733-947X(2005)131:10(771)","article-title":"Dynamic Wavelet Neural Network Model for Traffic Flow Forecasting","volume":"131","author":"Jiang","year":"2005","journal-title":"J. Transp. Eng."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1080\/15472450600798551","article-title":"A Wavelet Network Model for Short-Term Traffic Volume Forecasting","volume":"10","author":"Xie","year":"2006","journal-title":"J. Intell. Transp. Syst."},{"key":"ref_24","first-page":"3","article-title":"STL: A Seasonal-Trend Decomposition Procedure Based on Loess","volume":"6","author":"Cleveland","year":"1990","journal-title":"J. Off. Stat."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Yuan, F., Fan, Y., Bing, X., Tian, Z., Yuan, C., and Li, Y. (2025). A Decomposition-Driven Hybrid Framework Based on STL for Accurate Traffic Flow Forecasting. arXiv.","DOI":"10.21203\/rs.3.rs-7941600\/v1"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1080\/00031305.2017.1380080","article-title":"Forecasting at Scale","volume":"72","author":"Taylor","year":"2018","journal-title":"Am. Stat."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Wang, Z., Chu, R., Zhang, M., Wang, X., and Luan, S. (2020). An Improved Hybrid Highway Traffic Flow Prediction Model Based on Machine Learning. Sustainability, 12.","DOI":"10.3390\/su12208298"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wu, X., Fu, S., and He, Z. (2023). Research on Short-Term Traffic Flow Combination Prediction Based on CEEMDAN and Machine Learning. Appl. Sci., 13.","DOI":"10.3390\/app13010308"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"129870","DOI":"10.1016\/j.physa.2024.129870","article-title":"Short-term traffic flow prediction based on hybrid decomposition optimization and deep extreme learning machine","volume":"647","author":"Zhao","year":"2024","journal-title":"Phys. A"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Li, D., Feng, Y., and Chen, Y. (2024, January 28\u201330). Research on Traffic Flow Prediction Based on the PLO-ICEEMDAN-KAN Model. Proceedings of the 13th International Conference on Transportation and Traffic Engineering (ICTTE 2024), Wuhan, China.","DOI":"10.1049\/icp.2025.0515"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1389","DOI":"10.1007\/s11771-022-5000-2","article-title":"Hourly traffic flow forecasting using a new hybrid modelling method","volume":"29","author":"Liu","year":"2022","journal-title":"J. Cent. South Univ."},{"key":"ref_32","first-page":"97088","article-title":"Short-Term Traffic Flow Prediction Based on VMD and IDBO-LSTM","volume":"11","author":"Zhao","year":"2023","journal-title":"IEEE Access"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Bing, Q., Zhao, P., Ren, C., Wang, X., and Zhao, Y. (2024). Short-Term Traffic Flow Forecasting Method Based on Secondary Decomposition and Conventional Neural Network\u2013Transformer. Sustainability, 16.","DOI":"10.3390\/su16114567"},{"key":"ref_34","unstructured":"Manibardo, E.L., La\u00f1a, I., and Del Ser, J. (2020). Deep Learning for Road Traffic Forecasting: Does it Make a Difference?. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Grinsztajn, L., Oyallon, E., and Varoquaux, G. (2022). Why do tree-based models still outperform deep learning on tabular data?. arXiv.","DOI":"10.52202\/068431-0037"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"103607","DOI":"10.1016\/j.trc.2022.103607","article-title":"Estimate the limit of predictability in short-term traffic forecasting: An entropy-based approach","volume":"138","author":"Li","year":"2022","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_37","unstructured":"Rahaman, N., Baratin, A., Arpit, D., Draxler, F., Lin, M., Hamprecht, F.A., Bengio, Y., and Courville, A. (2019). On the Spectral Bias of Neural Networks. arXiv."},{"key":"ref_38","unstructured":"Elsayed, S., Thyssens, D., Rashed, A., Jomaa, H.S., and Schmidt-Thieme, L. (2021). Do We Really Need Deep Learning Models for Time Series Forecasting?. arXiv."},{"key":"ref_39","unstructured":"Uzel, Z. (2023). Comparative Analysis of LSTM, ARIMA, and Facebook\u2019s Prophet for Traffic Forecasting: Advancements, Challenges, and Limitations. [Bachelor\u2019s Thesis, Delft University of Technology]."}],"container-title":["Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-8954\/14\/5\/561\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T16:34:14Z","timestamp":1779208454000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-8954\/14\/5\/561"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,15]]},"references-count":39,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["systems14050561"],"URL":"https:\/\/doi.org\/10.3390\/systems14050561","relation":{},"ISSN":["2079-8954"],"issn-type":[{"value":"2079-8954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,15]]}}}