EIREducational Innovation Research3029-18443029-1852Bio-Byword Scientific Publishing Pty. Ltd.10.18063/EIR.v4i4.1995ArticleResearch on an Automated Intraday Liquidity Scheduling Strategy for Finance Companies Based on Deep Reinforcement Learninghttps://artdesignp.com/journal/EIR/4/4/10.18063/EIR.v4i4.1995GeBin2026442026-04-26This study rigorously formulates the complex fund-scheduling problem as a Markov decision process (MDP). It constructs a state space that integrates real-time and forecast information, an atomic action space that conforms to business logic, and a reward function that balances long-term returns against immediate risk. To address the curse of dimensionality and the credit-assignment problem in coordinated scheduling among multiple fund units, a multi-agent deep deterministic policy gradient (MADDPG) algorithm is adopted. Under a centralized-training and decentralized-execution framework, the algorithm reconciles global optimization with decentralized decision-making. In addition, a difference-reward mechanism and Kalman filtering are used to accurately measure each agent’s individual contribution and reduce the impact of environmental noise on reward signals. The results show that, compared with a static rule engine and a conventional linear programming method, the proposed deep reinforcement learning strategy reduces average daily funding costs by 50.4%, lowers the payment failure rate to 0.002%, and maintains a high liquidity buffer adequacy ratio. The strategy also demonstrates clear advantages in decision timeliness, collaborative handling of complex instructions, and self-adaptation potential, thereby providing an innovative pathway for finance-company fund scheduling to progress from intelligentization to automation.fund scheduling, Markov decision process, reward function, Kalman filtering, finance company

[1] Wang YZ, Song X B, Sun Y, et al., 2025, A Survey of Capital Efficiency and Financial Risk among Chinese Listed Companies: 2024. Accounting Research, 2025(12): 180-188. [2] Jiang AL, 2025, Practice of Building a World-Class Financial Management System in Company A, a Financial Leasing Company. Finance & Accounting, 2025(15): 27-29. [3] Zhao M, Xie L, Lin WJ, et al., 2024, A Deep Reinforcement Learning Portfolio Model Based on a Dynamic Selection Predictor. Computer Science, 51(4): 344-352. [4] Long J, Xie L, Xu HJ, 2024, An Ensemble Deep Reinforcement Learning Portfolio Model. Journal of Computer Applications, 44(1): 300-310. [5] Bu Z, Zhang SF, Li XY, et al., 2023, Adaptive Stock Index Forecasting Based on Deep Reinforcement Learning. Journal of Management Sciences in China, 26(4): 148-174.