Quantooox
Author ProfileClaim This Author Profile
Prove ownership by publishing #HashtagPLUS and this profile link on your author page or an article under your byline. A moderator or admin will review the request before it merges into your real HashtagPLUS username.
π dev.toSource
Our score had a slightly positive rank IC but its long-short portfolio lost. Three reasons the two measures can point in different directions.
π dev.toSource
A walk-forward leaderboard of 12 model families on S&P 100 stocks. Deep learning did not beat price-vs-average-plus-momentum, and nothing was significant.
π dev.toSource
We froze one stock score design and tested it on the S&P 100 and the Nifty 50, each with a sealed final year. The results disagreed.
π dev.toSource
Maruti Suzuki's quarter shows how pre-tax margin, EBIT margin and EBITDA margin differ, and why a data pipeline must name the one it uses.
π dev.toSource
A portfolio can look good because of a single name or a single year. Two simple reports that expose it.
π dev.toSource
How we prove every daily score was published before the outcome was known, using free tools anyone can verify.
π dev.toSource
A financial language model reads headlines about each company. How we timed it, and why the tone came too late to help.
π dev.toSource
Predicting direction failed. Predicting how bumpy the market will be worked a little. LightGBM, HAR, GARCH and a foundation model compared.
π dev.toSource
Two numbers that tell you whether a ranking had skill, and whether the difference between two models is just noise.
π dev.toSource
Turnover quietly eats backtests. How we charge costs, and the 2x stress test that many strategies fail.