Finance × Math × Code — no compromises. ruthlessly shipping @alphanume_data
Joined November 2022
- Tweets538
- Following46
- Followers1.5K
- Likes80
Quant Galore retweeted
100 model picks over the last 20 sessions, each with its realized move written back into the row the next day
the scoreboard:
-> average absolute move: 7.46%
-> 56 moved more than 5%
-> 28 moved more than 10%
biggest catch: NBIS, 34.14%
ALT Terminal-style card: curl api.alphanume.com/v1/next-day-movers returns 20 sessions, 100 picks, mean absolute move 7.46%, 56 over 5%, 28 over 10%, biggest NBIS 34.14%.
Quant Galore retweeted
Portfolio Management 101:
1. Find factors that drive returns.
2. Measure them with principal component analysis
3. Isolate them by hedging beta:
• Get data
• Build a regression
• Short the market
Start a hedge fund.
Quant Galore retweeted
Pick hedges by minimizing statistical dependence to factor returns, not just linear correlation. HSIC measures dependence in RKHS and detects nonlinear links (tail co-moves, volatility coupling). Compute HSIC between candidate hedge returns and factor vector on a rolling window. Choose the hedge (or hedge basket) with the smallest HSIC, then size by usual risk objectives.
Quant Galore retweeted
"We propose an alternative “blended” approach, which assigns 50% weight to the 12-2 return and 50% weight to the 11-2 return, then sorts stocks into deciles based on the simple average. We generalize this approach for a rebalancing frequency of N months (assigning 1/N weight)."
Quant Galore retweeted
The MMer mispriced the parlay, but then continued selling over many trades and there was presumably no alert to a human or no human responded to the alert that says you've been lifted X times in Y seconds which I'd think is still a protection MMs code into their systems
Great article analyzing Kalshi combo/parlay data, and showing what happens to a market maker with a bug in their code:
news.delphimarkets.com/p/how…
Quant Galore retweeted
"Commodity futures liquidity is highly concentrated: out of a universe of 69 commodity futures, the 10 most liquid account for 70% of the total liquidity across all available commodity futures, with energy futures alone accounting for 55-65%."
quantica-capital.com/publica…
Quant Galore retweeted
Sharpe rises from 0.681 at K=3 to 0.929 at K=15, but Table 3 reports 0.802 at K=3 and 0.763 at K=15. Pitfalls, pitfalls everywhere...
Quant Galore retweeted
Notes: Closed-form identity relates variance to thermodynamic coupling. No fitted params. VRP is mispriced because pricing ignores the market's information geometry. 23 markets across 5 asset classes fit within 4.5×10⁻⁴. Thermodynamic coupling exposes predictability.
Quant Galore retweeted
Treat the pair/basket spread as a random variable with a rolling distribution. Each day you compare today’s (recent) spread sample to a reference historical sample using a kernel two-sample distance. MMD detects distribution shifts beyond mean/variance. Stop trading when the test rejects same distribution, because the spread state likely changed.
Quant Galore retweeted
A new Research Recap is out. Topics include:
➢ An improved commodity carry signal
➢ Long-short equity strategies
➢ Trading the EIA report with LLMs
➢ Predicting option returns with LLMs
➢ Trading on inflation betas
➢ Great blogs, industry research & podcasts
➢ ...and much more.
quantseeker.com/p/weekly-res…
Quant Galore retweeted
When Trend-Following Hits Capacity: A Case Study on Commodities
"The expected Sharpe using 69 commodity markets can be twice as high as when restricted to the 10 most liquid markets.
"It is difficult to fully capitalize on diversification benefits due to capacity constraints.
Quant Galore retweeted
As a grad student working on Hamiltonian systems in General Relativity, I often wondered what the phase-plane approach from dynamical systems theory could tell us about markets.
Today I submitted the third paper in that answer:
Information Geometry of Market Dynamics: A Pareto Frontier from Contact Geometry.
Preprint: papers.ssrn.com/sol3/papers.…
and code:
Zenodo: doi.org/10.5281/zenodo.19681…
Quant Galore retweeted
Cryptocurrencies: BTC-USD, same methodology as the paper's SPY figure, free yfinance data. Lyapunov ellipses predicted from the fit alone; they match the empirical density with no angle or scale tuning. k=0.211, Ω=1.154, R²=0.573. Sits on the frontier within 10⁻³.
Quant Galore retweeted
Correlation and Commodity Risk Premia (Fan, Zhang)
"A long-short correlation portfolio delivers positive average returns but is largely spanned by exposures to the aggregate market, hedging pressure, and skewness factors."
Quant Galore retweeted
Tax Benefits of Pre-Tax Alpha (Liberman, Sosner, Freitas)
"Pre-tax alpha enhances the tax benefits of tax-aware long-short beta-one equity strategies. The positive effect of pre-tax alpha on tax benefits strengthens with leverage and investment horizon."
Quant Galore retweeted
In today’s Macro Volatility Digest:
🔹Equity, rates, credit, and FX implied volatilities all fell below their long-term averages.
🔹SPX 1M call skew, a measure of demand for upside calls, has surged from near a 1-year low to now the 90th percentile high on the back of FOMO (see chart below).
🔹We’ve seen a notable pickup in retail activity in MGTN options recently, with retail flow now making up over 80% of the volume.
Download the full report: bit.ly/4vFNOHP
Quant Galore retweeted
Riskfolio-Lib is a library for making quantitative strategic asset allocation or portfolio optimization in Python.
Here's the link:
github.com/dcajasn/Riskfolio…
