# On the Predictive Accuracy of Neural Temporal Point Process Models for Continuous-time Event Data arXiv: https://arxiv.org/abs/2306.17066 ยท HTML: https://mlsanity.com/paper/2306.17066/ ## Key facts - Cited by 14 papers in the map (data through 14 Oct 2026). - Builds on 24 of its 57 references that are in the map. - First posted on arXiv 29 Jun 2023. ## Builds on (most cited first, 24 of 24) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017) - [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019) - [Accurate Uncertainties for Deep Learning Using Calibrated Regression](https://mlsanity.com/paper/1807.00263/) (2018) - [Time2Vec: Learning a Vector Representation of Time](https://mlsanity.com/paper/1907.05321/) (2019) - [Intensity-Free Learning of Temporal Point Processes](https://mlsanity.com/paper/1909.12127/) (2019) - [Fully Neural Network based Model for General Temporal Point Processes](https://mlsanity.com/paper/1905.09690/) (2019) - [Neural Temporal Point Processes: A Review](https://mlsanity.com/paper/2104.03528/) (2021) - [Modeling The Intensity Function Of Point Process Via Recurrent Neural Networks](https://mlsanity.com/paper/1705.08982/) (2017) - [Wasserstein Learning of Deep Generative Point Process Models](https://mlsanity.com/paper/1705.08051/) (2017) - [Lecture Notes: Temporal Point Processes and the Conditional Intensity Function](https://mlsanity.com/paper/1806.00221/) (2018) - [Neural Temporal Point Processes For Modelling Electronic Health Records](https://mlsanity.com/paper/2007.13794/) (2020) - [COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution](https://mlsanity.com/paper/1507.02293/) (2015) - [Deep Reinforcement Learning of Marked Temporal Point Processes](https://mlsanity.com/paper/1805.09360/) (2018) - [Fast and Flexible Temporal Point Processes with Triangular Maps](https://mlsanity.com/paper/2006.12631/) (2020) - [Exploring Generative Neural Temporal Point Process](https://mlsanity.com/paper/2208.01874/) (2022) - [Self-Attentive Hawkes Processes](https://mlsanity.com/paper/1907.07561/) (2019) - [Noise-Contrastive Estimation for Multivariate Point Processes](https://mlsanity.com/paper/2011.00717/) (2020) - [SIR-Hawkes: Linking Epidemic Models and Hawkes Processes to Model Diffusions in Finite Populations](https://mlsanity.com/paper/1711.01679/) (2017) - [User-Dependent Neural Sequence Models for Continuous-Time Event Data](https://mlsanity.com/paper/2011.03231/) (2020) - [An Empirical Study: Extensive Deep Temporal Point Process](https://mlsanity.com/paper/2110.09823/) (2021) - [The Multivariate Hawkes Process in High Dimensions: Beyond Mutual Excitation](https://mlsanity.com/paper/1707.04928/) (2017) - [Interacting Hawkes processes with multiplicative inhibition](https://mlsanity.com/paper/2105.10597/) (2021) - [Modeling Inter-Dependence Between Time and Mark in Multivariate Temporal Point Processes](https://mlsanity.com/paper/2210.15294/) (2022) ## Built on by (most cited first, 14 of 14) - [Add and Thin: Diffusion for Temporal Point Processes](https://mlsanity.com/paper/2311.01139/) (2023) - [Deep Continuous-Time State-Space Models for Marked Event Sequences](https://mlsanity.com/paper/2412.19634/) (2024) - [Interacting Diffusion Processes for Event Sequence Forecasting](https://mlsanity.com/paper/2310.17800/) (2023) - [EventFlow: Forecasting Temporal Point Processes with Flow Matching](https://mlsanity.com/paper/2410.07430/) (2024) - [Edit-Based Flow Matching for Temporal Point Processes](https://mlsanity.com/paper/2510.06050/) (2025) - [Distribution-Free Conformal Joint Prediction Regions for Neural Marked Temporal Point Processes](https://mlsanity.com/paper/2401.04612/) (2024) - [Advances in Temporal Point Processes: Bayesian, Neural, and LLM Approaches](https://mlsanity.com/paper/2501.14291/) (2025) - [Hyper Hawkes Processes: Interpretable Models of Marked Temporal Point Processes](https://mlsanity.com/paper/2511.01096/) (2025) - [On Your Mark, Get Set, Predict! Modeling Continuous-Time Dynamics of Cascades for Information Popularity Prediction](https://mlsanity.com/paper/2409.16623/) (2024) - [Preventing Conflicting Gradients in Neural Marked Temporal Point Processes](https://mlsanity.com/paper/2412.08590/) (2024) - [Edge Selection for the Effective use of Piecewise-Constant Distributions as Neural Network Outputs for Event Prediction](https://mlsanity.com/paper/2507.21616/) (2025) - [Latent Block-Diffusion Temporal Point Processes: A Semi-Autoregressive Framework for Asynchronous Event Sequence Generation](https://mlsanity.com/paper/2606.24982/) (2026) - [Certifying What Helps Customer-Return Timing: A Screen-and-Confirm Test for Conditioning Signals, and Why Decay Is Nearly Enough](https://mlsanity.com/paper/2608.11555/) (2026) - [Exact Phase-Type Point Processes for Certified Measurement and Prediction of Event Streams](https://mlsanity.com/paper/2610.14948/) (2026) ## Abstract (arXiv) Temporal Point Processes (TPPs) serve as the standard mathematical framework for modeling asynchronous event sequences in continuous time. However, classical TPP models are often constrained by strong assumptions, limiting their ability to capture complex real-world event dynamics. To overcome this limitation, researchers have proposed Neural TPPs, which leverage neural network parametrizations to offer more flexible and efficient modeling. While recent studies demonstrate the effectiveness of Neural TPPs, they often lack a unified setup, relying on different baselines, datasets, and experimental configurations. This makes it challenging to identify the key factors driving improvements in predictive accuracy, hindering research progress. To bridge this gap, we present a comprehensive large-scale experimental study that systematically evaluates the predictive accuracy of state-of-the-art neural TPP models. Our study encompasses multiple real-world and synthetic event sequence datasets, following a carefully designed unified setup. We thoroughly investigate the influence of major architectural components such as event encoding, history encoder, and decoder parametrization on both time and mark prediction tasks. Additionally, we delve into the less explored area of probabilistic calibration for neural TPP models. By analyzing our results, we draw insightful conclusions regarding the significance of history size and the impact of architectural components on predictive accuracy. Furthermore, we shed light on the miscalibration of mark distributions in neural TPP models. Our study aims to provide valuable insights into the performance and characteristics of neural TPP models, contributing to a better understanding of their strengths and limitations.