# Deep Optimal Timing Strategies for Time Series

arXiv: https://arxiv.org/abs/2310.05479 · HTML: https://mlsanity.com/paper/2310.05479/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 9 Oct 2023.

## Builds on (most cited first, 22 of 22)

- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://mlsanity.com/paper/1704.04110/) (2017)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [Deep Transformer Models for Time Series Forecasting: The Influenza Prevalence Case](https://mlsanity.com/paper/2001.08317/) (2020)
- [EasyTPP: Towards Open Benchmarking Temporal Point Processes](https://mlsanity.com/paper/2307.08097/) (2023)
- [HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequences](https://mlsanity.com/paper/2210.01753/) (2022)
- [Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning](https://mlsanity.com/paper/2305.16646/) (2023)
- [Deep neural networks algorithms for stochastic control problems on finite horizon: convergence analysis](https://mlsanity.com/paper/1812.04300/) (2018)
- [Bellman Meets Hawkes: Model-Based Reinforcement Learning via Temporal Point Processes](https://mlsanity.com/paper/2201.12569/) (2022)
- [Learning in structured MDPs with convex cost functions: Improved regret bounds for inventory management](https://mlsanity.com/paper/1905.04337/) (2019)
- [Solving high-dimensional optimal stopping problems using deep learning](https://mlsanity.com/paper/1908.01602/) (2019)
- [A Graph Regularized Point Process Model For Event Propagation Sequence](https://mlsanity.com/paper/2211.11758/) (2022)
- [A Meta Reinforcement Learning Approach for Predictive Autoscaling in the Cloud](https://mlsanity.com/paper/2205.15795/) (2022)
- [Interpretable Optimal Stopping](https://mlsanity.com/paper/1812.07211/) (2018)
- [Deep Learning for Ranking Response Surfaces with Applications to Optimal Stopping Problems](https://mlsanity.com/paper/1901.03478/) (2019)
- [Continual Learning in Predictive Autoscaling](https://mlsanity.com/paper/2307.15941/) (2023)
- [Zap Q-Learning for Optimal Stopping Time Problems](https://mlsanity.com/paper/1904.11538/) (2019)
- [Solving optimal stopping problems with Deep Q-Learning](https://mlsanity.com/paper/2101.09682/) (2021)
- [DeepVar: An End-to-End Deep Learning Approach for Genomic Variant Recognition in Biomedical Literature](https://mlsanity.com/paper/2006.08338/) (2020)
- [Optimal Stopping with Gaussian Processes](https://mlsanity.com/paper/2209.14738/) (2022)
- [Automatic Deduction Path Learning via Reinforcement Learning with Environmental Correction](https://mlsanity.com/paper/2306.10083/) (2023)
- [Optimal Timing of Decisions: A General Theory Based on Continuation Values](https://mlsanity.com/paper/1703.09832/) (2017)

## Built on by (most cited first, 2 of 2)

- [ROMAS: A Role-Based Multi-Agent System for Database monitoring and Planning](https://mlsanity.com/paper/2412.13520/) (2024)
- [DORAEMON: A Unified Library for Visual Object Modeling and Representation Learning at Scale](https://mlsanity.com/paper/2511.04394/) (2025)

## Abstract (arXiv)

Deciding the best future execution time is a critical task in many business activities while evolving time series forecasting, and optimal timing strategy provides such a solution, which is driven by observed data. This solution has plenty of valuable applications to reduce the operation costs. In this paper, we propose a mechanism that combines a probabilistic time series forecasting task and an optimal timing decision task as a first systematic attempt to tackle these practical problems with both solid theoretical foundation and real-world flexibility. Specifically, it generates the future paths of the underlying time series via probabilistic forecasting algorithms, which does not need a sophisticated mathematical dynamic model relying on strong prior knowledge as most other common practices. In order to find the optimal execution time, we formulate the decision task as an optimal stopping problem, and employ a recurrent neural network structure (RNN) to approximate the optimal times. Github repository: urlgithub.com/ChenPopper/optimaltimingTSF.