Author

@hughesanalytics hughesanalytics

Quant trader narrating a self-built ML long/short basket with AI-hardware depth

Runs and live-narrates an ML-driven multi-sector long/short

trader score
-0.80
hit rate
50%
mean α
-0.22%
signals 14d
58

Grade = how their written analysis reads (A best). Trader score = how their last-20 timestamped calls performed vs SPY.

Their picks, scored

Across their last 20 scored bets: 50% hit rate, -0.22% mean alpha, trader score -0.80. Their last-14d mentions, direction-adjusted, have moved +0.5% since posting (mean over 42 mentions with price data).

Recent signals15receipts included
date (PT)tickerauthorsentwhat they saidsince thenreceipt
2026-08-27NVDA@hughesanalytics+0.00References an NVDA balance point visible only in the attached chart.-4.6%
2026-08-27MS@hughesanalytics-0.15Mocks the quality of estimates produced by someone employed at Morgan Stanley.-0.0%
2026-08-24·@hughesanalytics·Author argues trader-focused SaaS has weak defensibility unless its technical moat is deep.·
2026-08-21SPY@hughesanalytics+0.30Neural-net signal flipped SPY from mildly bearish to mildly bullish and tagged it oversold.+0.5%
2026-08-20HON@hughesanalytics+0.00HON stands out in an industrials screen, but direction requires the chart.-0.4%
2026-08-20·@hughesanalytics·Sector model improves for communications, staples and healthcare but worsens elsewhere.·
2026-08-20TLT@hughesanalytics+0.00ETF algorithm is focusing on GDX and TLT, but direction is only visible in the chart.+0.7%
2026-08-20GDX@hughesanalytics+0.00ETF algorithm is focusing on GDX and TLT, but direction is only visible in the chart.-0.2%
2026-08-20·@hughesanalytics·Gold miners, healthcare and energy are leading an active session.·
2026-08-20DE@hughesanalytics+0.00Flags large opposite-direction anomalies in WMT and DE without specifying which is positive.+1.5%
2026-08-20WMT@hughesanalytics+0.00Flags large opposite-direction anomalies in WMT and DE without specifying which is positive.-0.7%
2026-08-20·@hughesanalytics·Announces an incoming, less technology-heavy and more balanced model.·
2026-08-20ES_F@hughesanalytics-0.60Reports deeper downside trading and identifies support at 7631.·
2026-08-20·@hughesanalytics·Reports a model running at about 70 tokens/sec on two R9700 GPUs and outperforming Qwen 3.6-35B Q8.·
2026-08-20MRK@hughesanalytics-0.30Says MRK is near a cycle high with multiple cycle peaks expected by the weekend.-0.4%

Grade is our human read-worthiness rating; trader score is a rolling 20-bet hit-rate/alpha composite — different things, often disagreeing. “Since then” is direction-unaware in the table; the summary line above adjusts for which way they leaned.