Inductive Transportation Origin-Destination Demand Forecasting via Bayesian Destination-Choice Modeling

References

• Ashok K, Ben-Akiva ME (2000) Alternative approaches for real-time estimation and prediction of time-dependent origin-destination flows. Transportation Sci. 34(1):21–36.Link, Google Scholar
• Ben-Akiva ME, Lerman SR (1985) Discrete Choice Analysis: Theory and Application to Travel Demand, Transportation Studies, vol. 9 (MIT Press, Cambridge, MA).Google Scholar
• Bertsimas D, Ng YS, Yan J (2020) Joint frequency-setting and pricing optimization on multimodal transit networks at scale. Transportation Sci. 54(3):839–853.Link, Google Scholar
• Bertsimas D, Ng YS, Yan J (2021) Data-driven transit network design at scale. Oper. Res. 69(4):1118–1133.Link, Google Scholar
• Bhattacharjee D, Sinha KC, Krogmeier JV (2001) Modeling the effects of traveler information on freeway origin–destination demand prediction. Transportation Res. Part C Emerging Tech. 9(6):381–398.Crossref, Google Scholar
• Brandstätter G, Leitner M, Ljubić I (2020) Location of charging stations in electric car sharing systems. Transportation Sci. 54(5):1408–1438.Link, Google Scholar
• Chen Y, Liu Y (2023) Integrated optimization of planning and operations for shared autonomous electric vehicle systems. Transportation Sci. 57(1):106–134.Link, Google Scholar
• Chen X, Sun L (2021) Bayesian temporal factorization for multidimensional time series prediction. IEEE Trans. Pattern Anal. Machine Intelligence 44(9):4659–4673.Google Scholar
• Chen X, He Z, Sun L (2019) A Bayesian tensor decomposition approach for spatiotemporal traffic data imputation. Transportation Res. Part C Emerging Tech. 98:73–84.Crossref, Google Scholar
• Chen X, Yang J, Sun L (2020) A nonconvex low-rank tensor completion model for spatiotemporal traffic data imputation. Transportation Res. Part C Emerging Tech. 117:102673.Crossref, Google Scholar
• Chen X, Zhang C, Chen X, Saunier N, Sun L (2023) Discovering dynamic patterns from spatiotemporal data with time-varying low-rank autoregression. IEEE Trans. Knowledge Data Engrg. 36(2):504–517.Google Scholar
• Chen X, Zhang C, Zhao XL, Saunier N, Sun L (2025) Forecasting sparse movement speed of urban road networks with nonstationary temporal matrix factorization. Transportation Sci. 59(3):670–687.Abstract, Google Scholar
• Cheng Z, Trepanier M, Sun L (2022) Real-time forecasting of metro origin-destination matrices with high-order weighted dynamic mode decomposition. Transportation Sci. 56(4):904–918.Link, Google Scholar
• Chu W, Ghahramani Z (2009) Probabilistic models for incomplete multi-dimensional arrays. van Dyk D, Welling M, eds. Proc. 12th Internat. Conf. Artificial Intelligence Statist. (PMLR, New York), 89–96.Google Scholar
• Chu KF, Lam AY, Li VO (2019) Deep multi-scale convolutional LSTM network for travel demand and origin-destination predictions. IEEE Trans. Intelligent Transportation Systems 21(8):3219–3232.Crossref, Google Scholar
• Crainic TG, Hewitt M, Toulouse M, Vu DM (2016) Service network design with resource constraints. Transportation Sci. 50(4):1380–1393.Link, Google Scholar
• de Dios Ortúzar J, Willumsen LG (2024) Modelling Transport (John Wiley & Sons, Hoboken, NJ).Google Scholar
• Ding F, Zhao Z, Wang Y, Namgung M, Lee J, Li T (2026) Origin-destination flow generation for metro network expansion using spatiotemporal gated graph neural networks. Transportation Res. Part C Emerging Tech. 188:105677.Crossref, Google Scholar
• Fik TJ, Mulligan GF (1990) Spatial flows and competing central places: Towards a general theory of hierarchical interaction. Environ. Planning A Econom. Space 22(4):527–549.Crossref, Google Scholar
• Girolami M, Calderhead B (2011) Riemann manifold langevin and hamiltonian monte carlo methods. J. Royal Statist. Soc. Series B: Statist. Methodology 73(2):123–214. Crossref, Google Scholar
• Godbersen G, Kolisch R, Schiffer M (2024) Robust charging network planning for metropolitan taxi fleets. Transportation Sci. 58(2):295–314.Link, Google Scholar
• Gong Y, Li Z, Zhang J, Liu W, Zheng Y (2020) Online spatio-temporal crowd flow distribution prediction for complex metro system. IEEE Trans. Knowledge Data Engrg. 34(2):865–880.Crossref, Google Scholar
• He S, Shin KG (2020) Dynamic flow distribution prediction for urban dockless e-scooter sharing reconfiguration. Huang Y, King I, Liu T-Y, van Steen M, eds. Proc. Web Conf. 2020 (Association for Computing Machinery, New York), 133–143.Google Scholar
• Heanue KE, Pyers CE (1966) A comparative evaluation of trip distribution procedures. Highway Res. Record 114(35):11–14.Google Scholar
• Hu C, Rai P, Chen C, Harding M, Carin L (2015) Scalable Bayesian non-negative tensor factorization for massive count data. Appice A, Rodrigues P, Santos Costa V, Gama J, Jorge A, Soares C, eds. Machine Learn. Knowledge Discovery Databases. Joint Eur. Conf. Machine Learn. Knowledge Discovery Databases (Springer, Cham, Switzerland), 53–70.Google Scholar
• Ke J, Qin X, Yang H, Zheng Z, Zhu Z, Ye J (2021) Predicting origin-destination ride-sourcing demand with a spatio-temporal encoder-decoder residual multi-graph convolutional network. Transportation Res. Part C Emerging Tech. 122:102858.Crossref, Google Scholar
• Kolda TG, Bader BW (2009) Tensor decompositions and applications. SIAM Rev. 51(3):455–500.Crossref, Google Scholar
• Lei M, Sun L (2025) Low-rank tensor learning for spatiotemporal traffic and mobility data: A survey. Artificial Intelligence Transportation 3–4:100035.Crossref, Google Scholar
• Lei M, Labbe A, Sun L (2025) Scalable spatiotemporally varying coefficient modeling with Bayesian kernelized tensor regression. Bayesian Anal. 20(3):919–947.Crossref, Google Scholar
• Lei M, Labbe A, Wu Y, Sun L (2022) Bayesian kernelized matrix factorization for spatiotemporal traffic data imputation and kriging. IEEE Trans. Intelligent Transportation Systems 23(10):18962–18974.Crossref, Google Scholar
• Li Y, Zheng Y (2019) Citywide bike usage prediction in a bike-sharing system. IEEE Trans. Knowledge Data Engrg. 32(6):1079–1091.Crossref, Google Scholar
• Li X, Sun R, Sharpnack J, Fan Y (2023) Understanding origin-destination ride demand with interpretable and scalable nonnegative tensor decomposition. Transportation Sci. 57(6):1473–1495.Abstract, Google Scholar
• Liang Y, Zhao Z, Webster C (2024) Generating sparse origin-destination flows on shared mobility networks using probabilistic graph neural networks. Sustainable Cities Soc. 114:105777.Crossref, Google Scholar
• Liang Y, Ding F, Huang G, Zhao Z (2023) Deep trip generation with graph neural networks for bike sharing system expansion. Transportation Res. Part C Emerging Tech. 154:104241.Crossref, Google Scholar
• Liang Y, Zhao Z, Ding F, Tang Y, He Z (2024) Time-dependent trip generation for bike sharing planning: A multi-task memory-augmented graph neural network. Inform. Fusion 106:102294.Crossref, Google Scholar
• Liu L, Qiu Z, Li G, Wang Q, Ouyang W, Lin L (2019) Contextualized spatial–temporal network for taxi origin-destination demand prediction. IEEE Trans. Intelligent Transportation Systems 20(10):3875–3887.Crossref, Google Scholar
• Liu J, Sun L, Li Q, Ming J, Liu Y, Xiong H (2017) Functional zone based hierarchical demand prediction for bike system expansion. Proc. 23rd ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining (Association for Computing Machinery, New York), 957–966.Google Scholar
• Liu L, Zhu Y, Li G, Wu Z, Bai L, Lin L (2023) Online metro origin-destination prediction via heterogeneous information aggregation. IEEE Trans. Pattern Anal. Machine Intelligence 45(3):3574–3589.Google Scholar
• Luo M, Wen H, Luo Y, Du B, Klemmer K, Zhu H (2019) Dynamic demand prediction for expanding electric vehicle sharing systems: A graph sequence learning approach. Preprint, submitted March 10, https://arxiv.org/abs/1903.04051v1.Google Scholar
• Mak HY, Rong Y, Shen ZJM (2013) Infrastructure planning for electric vehicles with battery swapping. Management Sci. 59(7):1557–1575.Link, Google Scholar
• McNally MG (2007) The Four-Step Model. Handbook of Transport Modelling, vol. 1 (Emerald Group Publishing Limited, Leeds, UK), 35–53.Crossref, Google Scholar
• Murray I, Adams RP (2010) Slice sampling covariance hyperparameters of latent Gaussian models. Lafferty JD, Williams CKI, Shawe-Taylor J, Zemel RS, Culotta A, eds. Adv. Neural Inform. Processing Systems 23 (Curran Associates, Red Hook, NY), 1732–1740.Google Scholar
• Neal RM (2003) Slice sampling. Ann. Statist. 31(3):705–767.Crossref, Google Scholar
• Neumann-Saavedra BA, Crainic TG, Gendron B, Mattfeld DC, Römer M (2020) Integrating resource management in service network design for bike-sharing systems. Transportation Sci. 54(5):1251–1271.Link, Google Scholar
• Noursalehi P, Koutsopoulos HN, Zhao J (2021) Dynamic origin-destination prediction in urban rail systems: A multi-resolution spatio-temporal deep learning approach. IEEE Trans. Intelligent Transportation Systems 23(6):5106–5115.Crossref, Google Scholar
• Papaspiliopoulos O, Roberts GO, Sköld M (2007) A general framework for the parametrization of hierarchical models. Statist. Sci. 22(1):59–73.Crossref, Google Scholar
• Rai P, Hu C, Harding M, Carin L (2015) Scalable probabilistic tensor factorization for binary and count data. Yang Q, Wooldridge M, eds. IJCAI’15 Proc. 24th Internat. Conf. Artificial Intelligence (AAAI Press, Washington, DC), 3770–3776.Google Scholar
• Rasmussen CE, Williams CKI (2005) Gaussian Processes for Machine Learning (MIT Press, Cambridge, MA).Google Scholar
• Ren J, Xie Q (2017) Efficient OD trip matrix prediction based on tensor decomposition. 2017 18th IEEE Internat. Conf. Mobile Data Management (MDM 2017) (IEEE, New York), 180–185.Google Scholar
• Ruiter ER (1967) Toward a better understanding of the intervening opportunities model. Transportation Res. 1(1):47–56.Crossref, Google Scholar
• Schein A, Paisley J, Blei DM, Wallach H (2015) Bayesian Poisson tensor factorization for inferring multilateral relations from sparse dyadic event counts. Proc. 21st ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining (Association for Computing Machinery, New York), 1045–1054.Google Scholar
• Schneider M (1959) Gravity models and trip distribution theory. Papers Regional Sci. 5(1):51–56.Crossref, Google Scholar
• Sergin ND, Hu J, Li Z, Zhang C, Tsung F, Yan H (2025) Low-rank robust subspace tensor clustering for metro passenger flow modeling. INFORMS J. Data Sci. 4(1):33–50.Link, Google Scholar
• Shen L, Shao Z, Yu Y, Chen X (2021) Hybrid approach combining modified gravity model and deep learning for short-term forecasting of metro transit passenger flows. Transportation Res. Record 2675(1):25–38.Crossref, Google Scholar
• Simini F, Barlacchi G, Luca M, Pappalardo L (2021) A deep gravity model for mobility flows generation. Nature Comm. 12(1):6576.Crossref, Google Scholar
• Simini F, González MC, Maritan A, Barabási AL (2012) A universal model for mobility and migration patterns. Nature 484(7392):96–100.Crossref, Google Scholar
• Stolf F, Canale A (2026) Bayesian adaptive tucker decompositions for tensor factorization. J. Comput. Graphical Statist. 35(1):119–128.Crossref, Google Scholar
• Stouffer SA (1940) Intervening opportunities: A theory relating mobility and distance. Amer. Sociol. Rev. 5(6):845–867.Crossref, Google Scholar
• Sun L, Axhausen KW (2016) Understanding urban mobility patterns with a probabilistic tensor factorization framework. Transportation Res. Part B Methodological 91:511–524.Crossref, Google Scholar
• Wang L, Jin JG, Sibul G, Wei Y (2023) Designing metro network expansion: Deterministic and robust optimization models. Networks Spatial Econom. 23(1):317–347.Crossref, Google Scholar
• Wilson AG (1967) A statistical theory of spatial distribution models. Transportation Res. 1(3):253–269.Crossref, Google Scholar
• Wilson AG (1974) Urban and Regional Models in Geography and Planning (Wiley, London).Google Scholar
• Wu Y, Zhuang D, Labbe A, Sun L (2021) Inductive graph neural networks for spatiotemporal kriging. Proc. AAAI Conf. Artificial Intelligence 35(5):4478–4485.Crossref, Google Scholar
• Xiong X, Ozbay K, Jin L, Feng C (2020) Dynamic origin-destination matrix prediction with line graph neural networks and Kalman filter. Transportation Res. Record 2674(8):491–503.Crossref, Google Scholar
• Xiong L, Chen X, Huang TK, Schneider J, Carbonell JG (2010) Temporal collaborative filtering with Bayesian probabilistic tensor factorization. Parthasarathy S, Liu B, Goethals B, Pei J, Kamath C, eds. Proc. 2010 SIAM Internat. Conf. Data Mining (SDM) (SIAM, Philadelphia), 211–222.Google Scholar
• Yadav R, Schmidt AM, Labbe A, Jeganathan P, Miranda-Moreno LF (2025) Scalable spatiotemporal modeling for bicycle count prediction. Preprint, submitted June 9, https://arxiv.org/abs/2506.07582.Google Scholar
• Yao X, Gao Y, Zhu D, Manley E, Wang J, Liu Y (2021) Spatial origin-destination flow imputation using graph convolutional networks. IEEE Trans. Intelligent Transportation Systems 22(12):7474–7484.Crossref, Google Scholar
• Yu Y, Meng XL (2011) To center or not to center: That is not the question—An ancillarity–sufficiency interweaving strategy (ASIS) for boosting MCMC efficiency. J. Comput. Graphical Statist. 20(3):531–570.Crossref, Google Scholar
• Zhao Q, Zhang L, Cichocki A (2015) Bayesian CP factorization of incomplete tensors with automatic rank determination. IEEE Trans. Pattern Anal. Machine Intelligence 37(9):1751–1763.Crossref, Google Scholar
• Zhao Y, Wen H, Zhang X, Luo M (2025) BGM: Demand prediction for expanding bike-sharing systems with dynamic graph modeling. Kwok J, ed. Proc. 34th Internat. Joint Conf. Artificial Intelligence (International Joint Conferences on Artificial Intelligence, Montreal), 10008–10016.Google Scholar
• Zhou X, Mahmassani HS (2007) A structural state space model for real-time traffic origin-destination demand estimation and prediction in a day-to-day learning framework. Transportation Res. Part B Methodological 41(8):823–840.Crossref, Google Scholar
• Zhou Q, Lu X, Gu J, Zheng Z, Jin B, Zhou J (2024) Explainable origin-destination crowd flow interpolation via variational multi-modal recurrent graph auto-encoder. Proc. AAAI Conf. Artificial Intelligence 38(8):9422–9430.Crossref, Google Scholar
• Zhuang D, Wang S, Koutsopoulos H, Zhao J (2022) Uncertainty quantification of sparse travel demand prediction with spatial-temporal graph neural networks. Proc. 28th ACM SIGKDD Conf. Knowledge Discovery Data Mining (Association for Computing Machinery, New York), 4639–4647.Google Scholar
• Zipf GK (1946) The P1 P2/D hypothesis: On the intercity movement of persons. Amer. Sociol. Rev. 11(6):677–686.Crossref, Google Scholar