1. Predicting the trips occurring in the future via big data
Topic：基于历史数据对于出租车市场中出行需求的时空预测
Abstract：利用历史的出租车数据（GAIA）对于未来各个城市区域分时段出现的需求数量进行预测
Involved Method：深度学习等时空预测模型
Key word： Prediction, Forecasting, passenger demand.
Reference：Ke, J. , Zheng, H. , Yang, H. , & Chen, X. . (2017). Short-term forecasting of passenger demand under on-demand ride services: a spatio-temporal deep learning approach. Transportation Research Part C: Emerging Technologies, 85, 591-608.
2. Resource rebanlance / fleet management
Topic：基于历史数据对于出租车辆进行调度与管理
Abstract：利用历史的订单数据（GAIA），对于出租车队进行预先的管理与调度，例如平峰期提前将车辆调往未来需求高的区域以达到未来更好的需求满足率。
Involved Method：深度强化学习，运筹优化
Key word：fleet management, dynamic scheduling
Reference：Kaixiang Lin, Renyu Zhao, Zhe Xu, and Jiayu Zhou. 2018. Efficient Large-Scale Fleet Management via Multi-Agent Deep Reinforcement Learning. In KDD ’18: The 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, August 19–23, 2018, London, United Kingdom. ACM.https://doi.org/10.1145/3219819.3219993
3. The optimal strategy for taxi drivers to earn more money
Topic：司机在出租车服务之中最优的策略
Abstract：利用历史的轨迹数据，探究出租车司机最优的寻单策略，出车时间，服务区域
Involved Method：强化学习，特征工程，运筹优化
Key word：GPS-data，Taxi strategies
Reference：(2015). Understanding taxi service strategies from taxi gps traces. IEEE Transactions on Intelligent Transportation Systems, 16(1), 123-135.
4. Subsidy and compensations in dispatching strategies
Topic： 出租车派车过程中的后悔补偿
Abstract：出租车服务过程之中，我们很有可能随着时间的推移，去变更之前的指派计划（因为有了更好的匹配方案），此时我们需要变更我们的派车计划，此时需要向已经匹配的司机/乘客来补偿多少钱，才可以使他们接受新的变更呢？
Involved Method：效用模型，匹配算法，稳定性理论
Key word：Taxi dispatch，Regret mechanism
Reference：Holger Billhardt, Alberto Fernández, Sascha Ossowski, Javier Palanca, Javier Bajo, Taxi dispatching strategies with compensations, Expert Systems with Applications, Volume 122, 2019, Pages 173-182.
