$CFOAI
Fading QuicklySnapshot Window: 2026-09-11 22:20 UTC ยท โ Back to Crypto Overview
Social Momentum Summary
Total Engagement - Comments: 0, Retweets: 0, Likes: 0, Impressions: 4
Verbatim Community Citations & Social Evidence 1 source posts analyzed
Can recursive OHLCV forecasting actually work Iโm wondering if this is a dumb idea or actually feasible. Say you give a model 20 trading days of OHLCV as input and have it dream the next day directly in interpretable space, meaning full Open, High, Low, Close and Volume rather than a latent state. After it predicts that day, you treat the prediction like it was a real market day and recalculate SMA20, SMA50 and SMA200 differentiably from the predicted close. Then you slide the 20-day input window one day to the right, so it becomes: 19 real days + 1 predicted day and predict the next full OHLCV day.