# HoTPP Benchmark: Are We Good at the Long Horizon Events Forecasting?

arXiv: https://arxiv.org/abs/2406.14341 · HTML: https://mlsanity.com/paper/2406.14341/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 62 references that are in the map.
- First posted on arXiv 20 Jun 2024.

## Builds on (most cited first, 28 of 28)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [Time Series Forecasting With Deep Learning: A Survey](https://mlsanity.com/paper/2004.13408/) (2020)
- [Transformer Hawkes Process](https://mlsanity.com/paper/2002.09291/) (2020)
- [Intensity-Free Learning of Temporal Point Processes](https://mlsanity.com/paper/1909.12127/) (2019)
- [TransTab: Learning Transferable Tabular Transformers Across Tables](https://mlsanity.com/paper/2205.09328/) (2022)
- [Fully Neural Network based Model for General Temporal Point Processes](https://mlsanity.com/paper/1905.09690/) (2019)
- [Modeling The Intensity Function Of Point Process Via Recurrent Neural Networks](https://mlsanity.com/paper/1705.08982/) (2017)
- [Transformer Embeddings of Irregularly Spaced Events and Their Participants](https://mlsanity.com/paper/2201.00044/) (2021)
- [Tabular Transformers for Modeling Multivariate Time Series](https://mlsanity.com/paper/2011.01843/) (2020)
- [SEISMIC: A Self-Exciting Point Process Model for Predicting Tweet Popularity](https://mlsanity.com/paper/1506.02594/) (2015)
- [EasyTPP: Towards Open Benchmarking Temporal Point Processes](https://mlsanity.com/paper/2307.08097/) (2023)
- [ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling](https://mlsanity.com/paper/2402.10635/) (2024)
- [HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequences](https://mlsanity.com/paper/2210.01753/) (2022)
- [Event Stream GPT: A Data Pre-processing and Modeling Library for Generative, Pre-trained Transformers over Continuous-time Sequences of Complex Events](https://mlsanity.com/paper/2306.11547/) (2023)
- [Imputing Missing Events in Continuous-Time Event Streams](https://mlsanity.com/paper/1905.05570/) (2019)
- [CoLES: Contrastive Learning for Event Sequences with Self-Supervision](https://mlsanity.com/paper/2002.08232/) (2020)
- [Exploring Generative Neural Temporal Point Process](https://mlsanity.com/paper/2208.01874/) (2022)
- [The harm of class imbalance corrections for risk prediction models: illustration and simulation using logistic regression](https://mlsanity.com/paper/2202.09101/) (2022)
- [Add and Thin: Diffusion for Temporal Point Processes](https://mlsanity.com/paper/2311.01139/) (2023)
- [Tick: a Python library for statistical learning, with a particular emphasis on time-dependent modelling](https://mlsanity.com/paper/1707.03003/) (2017)
- [Long Horizon Forecasting With Temporal Point Processes](https://mlsanity.com/paper/2101.02815/) (2021)
- [Non-Autoregressive Diffusion-based Temporal Point Processes for Continuous-Time Long-Term Event Prediction](https://mlsanity.com/paper/2311.01033/) (2023)
- [Modeling Events and Interactions through Temporal Processes -- A Survey](https://mlsanity.com/paper/2303.06067/) (2023)
- [TemporAI: Facilitating Machine Learning Innovation in Time Domain Tasks for Medicine](https://mlsanity.com/paper/2301.12260/) (2023)
- [PoPPy: A Point Process Toolbox Based on PyTorch](https://mlsanity.com/paper/1810.10122/) (2018)

## Built on by (most cited first, 13 of 13)

- [EBES: Easy Benchmarking for Event Sequences](https://mlsanity.com/paper/2410.03399/) (2024)
- [ESQA: Event Sequences Question Answering](https://mlsanity.com/paper/2407.12833/) (2024)
- [Unsupervised Ordering for Maximum Clique](https://mlsanity.com/paper/2503.21814/) (2025)
- [Integrating Sequential and Relational Modeling for User Events: Datasets and Prediction Tasks](https://mlsanity.com/paper/2510.11903/) (2025)
- [LSP-DETR: Efficient and Scalable Nuclei Segmentation in Whole-Slide Images](https://mlsanity.com/paper/2601.03163/) (2026)
- [Unsupervised Learning for Quadratic Assignment](https://mlsanity.com/paper/2503.20001/) (2025)
- [How to model Human Actions distribution with Event Sequence Data](https://mlsanity.com/paper/2510.05856/) (2025)
- [Speculative Sampling for Parametric Temporal Point Processes](https://mlsanity.com/paper/2510.20031/) (2025)
- [SCULPT: Constraint-Guided Pruned MCTS that Carves Efficient Paths for Mathematical Reasoning](https://mlsanity.com/paper/2601.12842/) (2026)
- [Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modeling](https://mlsanity.com/paper/2607.01022/) (2026)
- [When, Not How Much: Evaluating Time-Series Foundation Models on Sparse Events](https://mlsanity.com/paper/2609.39386/) (2026)
- [Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective](https://mlsanity.com/paper/2610.12586/) (2026)
- [Exact Phase-Type Point Processes for Certified Measurement and Prediction of Event Streams](https://mlsanity.com/paper/2610.14948/) (2026)

## Abstract (arXiv)

Forecasting multiple future events within a given time horizon is essential for applications in finance, retail, social networks, and healthcare. Marked Temporal Point Processes (MTPP) provide a principled framework to model both the timing and labels of events. However, most existing research focuses on predicting only the next event, leaving long-horizon forecasting largely underexplored. To address this gap, we introduce HoTPP, the first benchmark specifically designed to rigorously evaluate long-horizon predictions. We identify shortcomings in widely used evaluation metrics, propose a theoretically grounded T-mAP metric, present strong statistical baselines, and offer efficient implementations of popular models. Our empirical results demonstrate that modern MTPP approaches often underperform simple statistical baselines. Furthermore, we analyze the diversity of predicted sequences and find that most methods exhibit mode collapse. Finally, we analyze the impact of autoregression and intensity-based losses on prediction quality, and outline promising directions for future research. The HoTPP source code, hyperparameters, and full evaluation results are available at GitHub.