DealForge autonomously sources, scores, and writes investment memos on venture deals. Stop manually hunting.
1,180+ deals tracked · 22 AI investment memos · Updated daily
Show HN: Open load forecasts that beat US grid operators on 6 of 7 RTOs
Fine-tuned Chronos-2 on 7 years of EIA-930 demand + ASOS temperature for every US balancing authority that publishes a load series — 53 across the three interconnections.<p>On a 2025 hold-out (~61,000 hours), it beats the operators' own day-ahead submissions to EIA — the production forecasts they use to schedule generation — on 6 of 7 major RTOs. Macro MAE ~40% lower. The one loss is ISO-NE, whose forecasting is just very good (24h-ahead MASE 0.34). On the same window, CAISO and SPP operator submissions did worse than "same as yesterday."<p>The site plots the median + 80% PI band against the operator submission, with 48h of actuals running into the forecast.<p>Code, model on HF, operator-comparison benchmark reproduces from one script:<p>- <a href="https://github.com/tylergibbs1/surge" rel="nofollow">https://github.com/tylergibbs1/surge</a> - <a href="https://huggingface.co/Tylerbry1/surge-fm-v3" rel="nofollow">https://huggingface.co/Tylerbry1/surge-fm-v3</a>
The technical achievement of outperforming established RTO forecasts by 40% using foundation models is a massive signal of potential in the high-stakes energy trading and grid management market. However, the project currently lacks a commercial structure, a full team, and a clear monetization strategy, making it a high-alpha but high-risk pre-seed prospect.