Wednesday: how quants vs MFDs talk about risk. Today: How to actually CALCULATE it. Sortino, Max Drawdown, Time Under Water, in under 30 lines of Python. #FinTwit #QuantTwitter #WealthManagement #SystematicTrading $NIFTY #Risk #NASDAQ

A client asks: "Is this fund risky?" A quant and an MFD will give completely different answers. Here's the translation table between them. #FinTwit #QuantTwitter #WealthManagement

Most quant alpha today isn't coming from balance sheets or price charts. It's coming from parking lots. Shipping lanes. Credit card receipts. A thread on Alternative Data, the quiet edge reshaping systematic investing. #FinTwit #QuantTwitter #SystematicTrading $NIFTY #Risk

I find the quality of content on QuantTwitter disappointing. so in the next few weeks, I will be sharing novel stories about practitioners/legends, resources, anecdotes & many more to kickstart this initiative I would like to share one of the most valuable websites for quant:

I encourage all my QuantTwitter followers who shit on academic finance to read Cochrane’s AFA address. Academic finance concerns itself with very different topics than industry. I think most confusion arises bc industry types tend to read easy papers from crappy journals and not the more advanced stuff happening on the frontier, which is concerned with entirely different things than industry. static1.squarespace.com/stat…

@fordoglunk @elletwocache could yall signal boost please? I’m joining #quantTwitter and want to become an influencer

Would you trust an algorithm with your capital if it couldn’t explain why it made a trade? The biggest risk in modern quant trading is the "Black Box" Problem. Here is why.... #QuantTwitter #MachineLearning #DataScience #Trading #MintingM

🚀 Today, I’m excited to officially launch DataSetIQ — a platform built to transform how analysts, economists, and finance teams work with public macro & financial data. For years, access to high-quality dataset intelligence has been locked behind expensive ($30k–$50k/yr) terminals and fragmented data portals. So I built something new. DataSetIQ is now LIVE — a unified AI-powered intelligence layer for: Searching millions of economic & financial datasets Instantly generating structured AI briefs Identifying trends, cycles, risks, and anomalies Tracking dataset updates in real time Comparing global indicators in seconds Researching with a modern, clean workflow It’s fast, affordable, and built from the ground up to support both individual analysts and full research teams. You can explore it here: DataSetIQ.com Huge thank you to everyone who supported this journey. I’m excited for what comes next. #Fintwit #Macroeconomics #QuantTwitter #AltData #DataScience

Do strategies work better if you only trade the names that historically like that strategy? I was skeptical. I kept hearing this from Perry J. Kaufman and in my bubble (Max Martone). So I tested it. Setup (simple swing mean‑reversion): • If z‑score < ‑1 → go long next bar open • Exit when Close > Open (first green day) or after 5 bars (whichever comes first) Ranking idea: I ran this on each stock and tracked a running Sharpe (up to the day before the signal to avoid look‑ahead). That running Sharpe became the ranking metric. Final test (S&P 500, historical constituents): • Same entry/exit rules • Red line: trade only stocks whose running Sharpe > 1 for this strategy; pick the top 10 each day • Green line: trade the whole index, simply sorting by z‑score (deeper oversold first) Result (see chart): Filtering the universe to stocks that historically respond to mean reversion produced a near‑Sharpe ≈ 1 after costs. Trading everything by z‑score alone? The equity curve bleeds out—effectively bankrupt. Takeaways: • Universe selection is not a footnote; it’s an edge. • Signals are name‑dependent—some stocks are mean‑reverters, others are momentum‑driven. • Rank by behavioral fit (rolling, out‑of‑sample stats), not just by signal intensity. • This is a rich vein for further testing: different lookbacks, decay, re‑ranking cadence, position caps, and risk parity. If this kind of evidence‑first research helps, follow for more systematic tests and automation ideas. 📈 #QuantTwitter #SystematicTrading #MeanReversion #SP500

🚀 New All-Time Equity High! 📈 Linear Regression – LONG (PACK 1) keeps pressing higher in forward real-time. From May’s peak… another 4 months of relentless grind up. 🧠 Stats snapshot: • Annual Return: 35.0% • Winners: 65.9% • Max DD: -13.2% • % Positive Months: ~80% Packs 2 & 3 also available. ⚠️ Only 1 slot left — then closed. 👀 Next project? The SHORT pack. If you thought LONG was smooth, wait until both are combined. 🔥 📊 See it yourself 👉 🔗 ko-fi.com/s/256a86b7b8 #QuantTwitter #TradingEdge #AlgoTrading #EquityHigh

Poll time! Do you prefer backtest results as a thread or an article? 👇 Drop your backtest ideas in the replies — I’ll pick a few to run next! #NQ #Backtest #TradingStats #QuantTwitter

🧵 How I Trade $TSLA Using Dealer Flow, Gamma Traps, and Real Risk Zones This isn’t about trendlines. It’s about who’s forced to move size — and when. Here’s how I catch $TSLA trades before the breakout 👇 #TSLA #optionsflow #QuantTwitter

🚀 New Equity High Alert! 📈 Linear Regression – LONG (PACK 1) just hit a fresh all-time high in forward testing real-time! 🧠 Packs 2 & 3 also available — more edges, same consistency. ⚠️ Only 3 slots left — last chance to grab this research project! 👀 New project in the making... This time, we’re going SHORT. 📉 If you liked the LONG edge, wait until you see what happens when you combine both. Stay tuned. 🔥 📊 See it yourself 👉 🔗 ko-fi.com/s/256a86b7b8 #QuantTwitter #TradingEdge #Backtest #AlgoTrading #EquityHigh

Connors' RSI(2) strategy flips the script: buy pullbacks, not breakouts, sell oversold bounces, not support breaks. 📉 This mean-reversion model helps traders capitalize on short-term market moves. Python lets you easily tweak the system. Check out the GitHub code for your own fine-tuning and backtesting! 🔧📊 #RSI #MeanReversion #AlgoTrading #PythonFinance #QuantTwitter github.com/russs123/RSI/blob…

Join our Department & the @UNC Tar Heel community! We are hiring a Teaching Assistant Professor to teach statistics and research methods! Preferred start date is January 2021. #AcademicTwitter #QuantTwitter #StatsTwitter unc.peopleadmin.com/postings…

On my way to my first #SMEP Annual Meeting in Baltimore. Looking very much forward meeting everyone! #TeamMethods #QuantTwitter @EDMSatUMD #smep19

We’re so excited to host methodologists from all over for the #SMEP Annual Meeting in Baltimore this week. Welcome to Charm City! 🥳🍾 #TeamMethods #QuantTwitter

He’s got it out for QuantTwitter... poor guy needs to learn some python

Welcome back, @UMDCollegeofEd! We’re looking forward to another great year full of beautiful, beautiful statistics. #teamMethods #quantTwitter

Lol. Derivers test. Cc #quanttwitter