Summary of Hotpp Benchmark: Are We Good at the Long Horizon Events Forecasting?, by Ivan Karpukhin et al.
HoTPP Benchmark: Are We Good at the Long Horizon Events Forecasting?
by Ivan Karpukhin, Foma Shipilov, Andrey Savchenko
First submitted to arxiv on: 20 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed novel evaluation method for Marked Temporal Point Processes (MTPP) models is a temporal variant of mean Average Precision (mAP), called T-mAP. This approach addresses limitations of existing long-horizon evaluation metrics, such as inaccurate handling of false positives and false negatives. The study demonstrates that strong next-event prediction accuracy does not necessarily translate to good long-horizon forecasts, highlighting the need for specialized methods for each task. A benchmark, HoTPP, is released with large-scale datasets and optimized procedures for autoregressive and parallel inference. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us understand how to better predict when multiple events will happen in the future. Currently, we’re only looking at predicting the next event, but this isn’t always accurate. The researchers propose a new way to measure how well our predictions are doing by counting true positives, false positives, and false negatives over time. They also release a large dataset for other scientists to use to improve their own predictions. |
Keywords
» Artificial intelligence » Autoregressive » Inference » Mean average precision
