Rank Equity

Two years ago, I built a simple system based on just 7 factors. Since then, it’s been consistently outperforming. Backtests show it has outperformed every single year since 2002 — except 2019. I wrote a free e-book explaining the system. You can use it yourself. No paywall.

Stocks listed in a weakening currency, outperform. That means: investing in Turkey, Poland, Sweden. The more weakening the currency, the better. Unhedged that is. Crazy, right?

Over the past several months, I identified what I believe to be a previously undiscovered meta-factor. I'm not publishing this one yet. But the factor and research process that led me to finding it, will be in my book. For now, the intro E-book is already up for grabs. Free.

For professional clients, I'm always hunting for an edge. One I like: a factor that tracks how consistently companies return capital. It sums consecutive years of: • Buybacks • Dividend increases • Debt reductions Additions to the factors in the free e-book. No paywall.

I built this model about 3 years ago. Since then, it's EXCESS return vs the Russell 2000 were: 2023: +5.4% 2024: +8.2% 2025: +11.6% 2026 YTD: +8.2% 30 stocks. $500k+ median daily dollar volume. At 5% participation, 500% turnover, roughly 38M max AUM. Available to members.

@RankEquity I finally understand factor investing thanks to your ebook. Amazing work really. will be in line to buy the full book whenever you publish it. Great work

@nymfree Hi X.M., it is a comment like yours that I really do it all for. So thank you very much for taking the time to write it. It also gives me more enthusiasm to keep on writing the full book. Thanks again and all the best.

A subscriber wanted to link one of my example portfolios with their broker. So I offered it. 10 minutes to set up. $1M+ median dollar volume — liquidity is no issue here. Outperforming every year since 2002, except 2020. Another happy member.

@461ocean_com The ebook is up for grabs. Book under way :).

@RankEquity No book. All bullshit

Two years ago, I built a simple system based on just 7 factors. Since then, it’s been consistently outperforming. Backtests show it has outperformed every single year since 2002 — except 2019. I wrote a free e-book explaining the system. You can use it yourself. No paywall.

@Sebartha30 I'm a bit biased, but it's worth a read!

@RankEquity Explain it here. Nobody wants the ebook

@WolfhartInvest Personally, knowing it is long only - I would have conviction in the system. But each their own, of course. Levering up to 1.3x and taking a 30% position in TZA (very naïve hedge) would have resulted in a 30% max drawdown with 23% annualized and a beta of 0. Backtested, that is.

@RankEquity bit above 30% CAGR. that's awesome! 50% max drawdown is still hard though. looks ok in backtests, but when living through it, hard to keep conviction in the system

@MidnightLogic42 Check my bio, or send a dm :)

@RankEquity Where is the free book pls?

@systvest It is fascinating how my portfolios have almost no overlap with yours, but both have strong returns. Even using similar ways of investing.

📊📉📈 LOT of trades today... Short Strat $DOW $CPRT $IONQ ➡️ $APD $CPNG ExUS long $ALTN.L $DBA.MI ➡️ $EDRY $JOY.TO Global long $NDT.MI (trim) US long $CODA $ASRT $RFIL ➡️ $CVGI $ZDGE $ATNI Old vs. New Sector exposures see below: 🏥 + 🪙 reduce 🛢️ + ⚙️ + 📡 increase

@AlgoManX @Scifospace @P123Finance I get it. I think what is nice about an approach like this, is that it doesn't throw away features. A lot of 'factor engineering' approaches throw away factors when they are correlated and only keep a few. Why not bundle the correlated ones together, like you do here with PCA.

@RankEquity @Scifospace @P123Finance Since we never indicate direction or a target for the analysis it is necessary to have a few strong core (biased) features, if not, it should not work

@Scifospace came with a brilliant idea that I had to test. Run a PCA Analysis of Normalized Features (factors), decompose each component in the PCA analysis to be used as new factors for ranking systems in @P123Finance or as new AI factors. One night with no sleep💻and it's done!

When approaching new methods, I like to make little mindmaps. Mapping out how it relates to what I already know. How does Machine Learning in factor investing relate to classic linear ranking systems? Can I make it more intuitive?

Time to dip my toes into the machine learning side of factor investing. Will report back with results...

Replicated a version of this paper and got some interesting results. Volatility is a price. Prior research has shown that investors are often willing to overpay for protection, creating a persistent Volatility Risk Premium (VRP). A premium that has shown to be harvestable...

For any serious factor investor - the word 'Bitcoin' alone will make the eyes roll over. No cash flows, no fundamentals, sky high volatility. There's crypto exchanges going under. Retail madness. At the same time... you have seen that jumpy yellow graph go higher and higher. You have read about the effects of quantitative easing on major currency values. You have seen gold and real assets rise in value relative to the dollar. Perhaps you've wondered if there is a right way to get exposure. Perhaps you've pondered on a way to make the ride bearable. Perhaps you want to control the beast. That is exactly what Lovely Debasements sets out to do. The Lovely Debasements strategy invests in Bitcoin via the ETF IBIT, but does so in a way that seeks to limit drawdowns by adding five components: - Combining it in a portfolio with other assets that benefit from currency debasement and with similar volatility profiles: primarily levered exposure to gold, the Nasdaq 100, inverse treasury bonds, and short-term VIX futures; - Only investing in the top 3 out of 5 of the above assets based on a variety of momentum and sentiment measures; - Only investing in this top 3 when these assets themselves are trending above a variety of their own SMA's (simple moving averages) and allocating proportionally to defensive assets when they are trending lower than their SMA's; - Rotating the said defensive assets from short-term US treasuries bonds and bills to European bonds and silver depending on the trend of the US dollar index; - And most importantly, using inverse volatility weighting - where higher volatile assets get a lower weight. The strategy seeks to (1) allow a safer way to invest in Bitcoin via a diversified ETF portfolio and risk controls, (2) offer low - preferably negative - correlation to the S&P 500, (3) benefit from the scenario where the US would default on its debt obligations and/or the US central bank (FED) would resort to further quantitative easing and further currency debasement and (4) ensure easy tradability by diversifying over highly liquid instruments with upside in trending markets. Note that IBIT has been launched at the start of 2024.