https://quantarenas.com/Weekly arena reports, research articles and site updates.en https://quantarenas.com/changelog/https://quantarenas.com/changelog/#2026-11-11-685acdb0Wed, 11 Nov 2026 00:00:00 +0000Market regimes shows each market's trend, volatility and strategy positioning every trading day. The claim checker tests 34 popular trading sayings on daily data and gives each a verdict. Event replays show how the strategies behaved in 35 major market events since 2010, plus recent sell-offs detected automatically. Famous strategies re-runs 22 well-known public portfolios and rule sets on our ten markets and says what had to be adapted. https://quantarenas.com/reports/2026-w46/https://quantarenas.com/reports/2026-w46/#2026-11-10-c9e1b772Tue, 10 Nov 2026 00:00:00 +0000What moved in the arena during the week ending 2026-11-10: market moves, strategies that changed position, and the best and worst performers over the last month. https://quantarenas.com/changelog/https://quantarenas.com/changelog/#2026-11-08-0461ac3bSun, 08 Nov 2026 00:00:00 +0000An optional Ko-fi link now appears in the footer, at the end of research articles and beside prepared or verified browser downloads. Contributions support data updates, backtest verification and new tools. All existing free downloads remain available. The support provider opens only when you choose the link; no payment widget loads automatically. https://quantarenas.com/changelog/https://quantarenas.com/changelog/#2026-11-07-d8634a8eSat, 07 Nov 2026 00:00:00 +0000A new comparison worksheet keeps before and after on identical shared dates, separates strategy and allocation fees, and shows gross/net returns, recovery, downside sample counts and signed exposure overlap. Frozen share links retain the original evidence; optional named saves stay in this browser. Independent sleeves do not net trades across strategies. Financing, borrowing, funding, taxes and market impact remain excluded. https://quantarenas.com/changelog/https://quantarenas.com/changelog/#2026-11-07-9acfc23aSat, 07 Nov 2026 00:00:00 +0000All 576 supported strategy-market pairs now have separate 0, 5, 10 and 25 bp cost scenarios across seven windows. Strategies and matched benchmarks each pay charges on their own drift-adjusted one-way risky turnover after gross returns. Rankings compare identical asset universes, dates, input returns and window anchors; a basket labelled SPY is kept separate from single-market SPY. Fee totals use the disclosed initial-capital or start-close-capital units. Metrics use all original full-precision daily records, while curves are bounded display samples and metrics load by the selected universe. This independent fee-sensitivity view leaves existing before-cost Arena rankings intact. It models synthetic exposure charges, not actual broker fills or exact traded notional; financing, borrow, funding, taxes and market impact remain excluded. https://quantarenas.com/changelog/https://quantarenas.com/changelog/#2026-11-07-c8df46eaSat, 07 Nov 2026 00:00:00 +0000OpenAI and Anthropic each retain six unchanged rules. Their prompt, original replies and receipt metadata were verified publicly on 7 November 2026 at 00:20 UTC, before scheduling. Season 1 runs from 9 November 2026 through 6 February 2027. It is scheduled, with no performance yet; rankings require at least 20 observations in every required market and complete matching windows. Late entrants belong to a later season. https://quantarenas.com/reports/2026-w45/https://quantarenas.com/reports/2026-w45/#2026-11-06-465be86dFri, 06 Nov 2026 00:00:00 +0000What moved in the arena during the week ending 2026-11-06: market moves, strategies that changed position, and the best and worst performers over the last month. https://quantarenas.com/changelog/https://quantarenas.com/changelog/#2026-11-06-cd48a302Fri, 06 Nov 2026 00:00:00 +0000Two real CLI submissions, from OpenAI and Anthropic, now retain all six frozen rules each under one public prompt, with exact prompt/reply downloads, requested and reported model fields, freeze timestamps and operator-recorded receipts. The common-date season remains a draft: no start has been scheduled and no performance or rankings are published. Anthropic reports claude-sonnet-5 and discloses auxiliary claude-haiku-4-5-20251001 usage; the auxiliary purpose and underlying model revision are not established, and inference compute is not normalized across providers. The original single-assistant experiment remains separate with its original figures and disclosed execution-timing and rounded-input limitations. These CLI receipts are not provider-signed attestations. https://quantarenas.com/changelog/https://quantarenas.com/changelog/#2026-11-06-3772ad90Fri, 06 Nov 2026 00:00:00 +0000Evidence now covers all 72 strategies and 576 supported pairs, including signed per-asset basket holdings. Daily records, configurations and archived source can be downloaded on demand; the standalone tool can fetch inputs and regenerate rules when the original input fingerprint matches. Every current run has original-input recomputation proof across 2,394,468 observations, including 11 newly corrected runs. Ten monthly basket rules now decide on the first observed new-month session using the preceding observation, with the engine lag retained. The turn-of-month rule uses a disclosed weekday approximation, not an exchange-holiday calendar. These corrections change historical results; old immutable runs and correction links remain available. Costs remain zero in this baseline; synthetic targets and rebalancing are not broker fills. https://quantarenas.com/changelog/https://quantarenas.com/changelog/#2026-11-06-6d2dd59bFri, 06 Nov 2026 00:00:00 +0000Six representative strategies now have evidence bundles on SPY, gold and bitcoin: full-precision daily accounting, simulated position changes, actual selected parameters, source hashes and a standalone arithmetic replay script. The evidence index preserves prior corrected snapshots. Signals now come from engine targets rather than ratios of rounded returns, with target and effective exposure, per-market observation dates and independent data status. The current UTC date is excluded conservatively. Walk-forward boundary returns are recomputed from the previous published target, and skipped folds retain default targets; the evidence index quantifies these accounting changes. This is an 18-pair pilot, not full-site verification or broker fills. https://quantarenas.com/changelog/https://quantarenas.com/changelog/#2026-11-04-c5b6cfb3Wed, 04 Nov 2026 00:00:00 +0000Six trading rules written by an AI assistant, with every parameter fixed, are now tracked every trading day on nine markets against buy-and-hold and our 72 classic strategies. Because a language model may already know past markets, the ranking uses only results after 4 November 2026, the day the rules were frozen; the historical backtest is shown for reference only. https://quantarenas.com/changelog/https://quantarenas.com/changelog/#2026-11-04-2f7678f3Wed, 04 Nov 2026 00:00:00 +0000A guide to 18 widely used open-source projects for backtesting, live trading, crypto bots, machine learning and market data (Backtrader, vectorbt, LEAN, NautilusTrader, vn.py, Freqtrade, Qlib, FinRL, TradingAgents and more): what each is for, strengths, limitations, alternatives and seven head-to-head comparisons. GitHub stars, last commit, latest release and maintenance status are refreshed every week. https://quantarenas.com/changelog/https://quantarenas.com/changelog/#2026-11-04-4436c55bWed, 04 Nov 2026 00:00:00 +0000Every static page now has a subscribe box for the weekly Arena report (ranking changes, new signals and new research), sent by email through Buttondown. We also started counting anonymous usage events such as searches and comparisons with Umami, which uses no cookies. https://quantarenas.com/changelog/https://quantarenas.com/changelog/#2026-11-04-3079679aWed, 04 Nov 2026 00:00:00 +0000The site now publishes llms.txt, a plain-text guide for AI assistants and answer engines: what Quant Arena tests and how, the main pages, every live research article with its data date, the glossary and all strategy pages. It is rebuilt with the sitemap every day. https://quantarenas.com/changelog/https://quantarenas.com/changelog/#2026-11-04-541daf70Wed, 04 Nov 2026 00:00:00 +0000Strategy pages now compare the Sharpe ratio that the walk-forward parameters had on their training windows with what they earned in the following six months, and with the default parameters over the same months. They also show how many settings in the parameter grid had a positive Sharpe ratio. Across the 486 strategy-and-market pairs with parameters to tune, the median Sharpe ratio fell from 0.32 on the training windows to 0.19 out of sample; the walk-forward glossary entry has the details. https://quantarenas.com/changelog/https://quantarenas.com/changelog/#2026-11-04-c98395a5Wed, 04 Nov 2026 00:00:00 +0000All 1,063 converted EAs were re-run on four markets with hourly data from November 2025 to November 2026 (previously May 2025 to May 2026). 1,119 results are reliable enough to rank. This now happens automatically every month. https://quantarenas.com/research/luck-adjusted-sharpe-72-strategies/https://quantarenas.com/research/luck-adjusted-sharpe-72-strategies/#2026-11-03-5362071bTue, 03 Nov 2026 00:00:00 +0000104 strategy-and-market combinations look statistically convincing on their own. Once you account for the fact that we tested hundreds of them at the same time, the number drops to zero. Here is what that means for reading any leaderboard, including ours. https://quantarenas.com/research/free-mt5-expert-advisors-backtested/https://quantarenas.com/research/free-mt5-expert-advisors-backtested/#2026-11-03-96e71405Tue, 03 Nov 2026 00:00:00 +0000Free MetaTrader 5 EAs from the MQL5 CodeBase, converted automatically and tested on four markets for one year. More than half could not be converted at all. Of the 1,123 results we trust, about half made money — but on currencies the typical EA ended flat, only 30 EAs were profitable on all four markets, and one in five gold runs wiped out the account. https://quantarenas.com/research/which-strategies-survived-2022/https://quantarenas.com/research/which-strategies-survived-2022/#2026-11-03-a70bdc81Tue, 03 Nov 2026 00:00:00 +0000In the 2022 bear market SPY fell 24.5% from peak to trough. Every one of the 62 strategies we run on SPY lost less, and ten of them made money. Mean reversion held up best, momentum worst. Here is what the COVID crash and the late-2018 sell-off add to the picture. https://quantarenas.com/research/why-martingale-and-grid-eas-blow-up/https://quantarenas.com/research/why-martingale-and-grid-eas-blow-up/#2026-11-03-3d5012d9Tue, 03 Nov 2026 00:00:00 +0000Martingale and grid EAs make up 5% of the free MT5 Expert Advisors we review, but more than half of the ones we rate "dangerous". The reason is arithmetic: losing streaks of six to eight trades are normal — and that is exactly where doubling the position runs out of money. https://quantarenas.com/research/moving-average-strategies-bitcoin/https://quantarenas.com/research/moving-average-strategies-bitcoin/#2026-11-03-339d89b7Tue, 03 Nov 2026 00:00:00 +0000Over the last five years buy-and-hold bitcoin returned 7.2% a year with a 77% drawdown. Five of nine moving-average-style systems beat that return, and every one of them cut the worst drawdown. Over the full history the picture flips: almost nothing beats simply holding. https://quantarenas.com/research/turtle-trading-2021-2026/https://quantarenas.com/research/turtle-trading-2021-2026/#2026-11-03-d318518eTue, 03 Nov 2026 00:00:00 +0000Two breakout systems, ten markets, five years. Neither beat buy-and-hold on most markets, but the slower Donchian version had a smaller drawdown on nine of ten, and both made money on commodities in the 2022 bear market when stocks fell 25%. https://quantarenas.com/research/macd-vs-macd-rsi-filter/https://quantarenas.com/research/macd-vs-macd-rsi-filter/#2026-11-03-5cf444e1Tue, 03 Nov 2026 00:00:00 +0000Adding an RSI filter to a MACD crossover cut the maximum drawdown on nine of ten markets and reduced trading by 10–30%. It improved the Sharpe ratio on only five, and gave up return on the strongest trends — silver, bitcoin and ether. https://quantarenas.com/research/how-to-read-drawdown-ulcer-index-rolling-sharpe/https://quantarenas.com/research/how-to-read-drawdown-ulcer-index-rolling-sharpe/#2026-11-03-e9392161Tue, 03 Nov 2026 00:00:00 +0000Maximum drawdown tells you how deep the worst fall was, not how long you spent underwater or how often it happened. Two strategies on the S&P 500 with almost identical 10% drawdowns show why the Ulcer index and drawdown duration are worth a look — and why a single Sharpe ratio can mislead as much as a single drawdown. https://quantarenas.com/research/keltner-vs-bollinger/https://quantarenas.com/research/keltner-vs-bollinger/#2026-11-03-6b945b2cTue, 03 Nov 2026 00:00:00 +0000Two volatility-band strategies that do opposite things: one buys when price breaks out of a Keltner Channel, the other buys when price falls to the lower Bollinger Band. Over the last five years each had the better Sharpe ratio on exactly five of ten markets — and the split follows a clear pattern: breakouts won where prices trended, reversion won where they went back and forth. https://quantarenas.com/changelog/https://quantarenas.com/changelog/#2026-11-03-118c3cebTue, 03 Nov 2026 00:00:00 +0000For each market with a reliable backtest, EA pages now show the share of months with a gain and the best and worst month, with dates. EA backtests are also re-run every month on the latest twelve months of hourly data. https://quantarenas.com/reports/2026-w33/https://quantarenas.com/reports/2026-w33/#2026-08-14-6de32f6dFri, 14 Aug 2026 00:00:00 +0000What moved in the arena during the week ending 2026-08-14: market moves, strategies that changed position, and the best and worst performers over the last month. https://quantarenas.com/research/donchian-turtle-breakout/https://quantarenas.com/research/donchian-turtle-breakout/#2026-01-20-34581572Tue, 20 Jan 2026 00:00:00 +0000The Turtle system uses Donchian breakouts and risk based sizing to capture sustained trends. This research note explains the logic, market fit, and failure modes. https://quantarenas.com/research/supertrend-atr-trailing-stop/https://quantarenas.com/research/supertrend-atr-trailing-stop/#2026-01-20-7284c812Tue, 20 Jan 2026 00:00:00 +0000Supertrend uses ATR based bands to define trend flips and stops. This research note explains the signal mechanics, regime fit, and the risks of whipsaw. https://quantarenas.com/research/ichimoku-cloud-strategy/https://quantarenas.com/research/ichimoku-cloud-strategy/#2026-01-20-ece148caTue, 20 Jan 2026 00:00:00 +0000Ichimoku combines trend, momentum, and support into a single framework. This research note breaks down the components, signals, and common traps. https://quantarenas.com/research/rsi-mean-reversion/https://quantarenas.com/research/rsi-mean-reversion/#2026-01-19-fc873c38Mon, 19 Jan 2026 00:00:00 +0000RSI mean reversion looks for short term exhaustion and then fades the move. This research note covers the signal logic, market fit, and risk traps. https://quantarenas.com/research/ema-crossover-strategy/https://quantarenas.com/research/ema-crossover-strategy/#2026-01-13-60c08fa6Tue, 13 Jan 2026 00:00:00 +0000An in depth look at why exponential moving average crossovers persist, how to interpret their backtests, and when trend signals fail. https://quantarenas.com/research/parabolic-sar-strategy/https://quantarenas.com/research/parabolic-sar-strategy/#2026-01-13-963dc00dTue, 13 Jan 2026 00:00:00 +0000Parabolic SAR uses a trailing stop that accelerates with trend strength. This article explains why it works, when it fails, and how to read its backtests. https://quantarenas.com/research/volatility-breakout/https://quantarenas.com/research/volatility-breakout/#2026-01-13-c0bdb668Tue, 13 Jan 2026 00:00:00 +0000Volatility breakouts focus on price moves that escape a recent range. This guide explains the logic, the regimes where it works, and the traps to avoid. https://quantarenas.com/research/how-quantarenas-ranks-strategies/https://quantarenas.com/research/how-quantarenas-ranks-strategies/#2026-01-13-a7106d7bTue, 13 Jan 2026 00:00:00 +0000A full methodology essay on why the Arena Score blends multiple metrics, how stability is measured, and how to read results without overfitting.