Your money and securities remain in your brokerage account at all times. ALGORA1 never takes custody of your funds, holds your securities, or transfers your assets into an ALGORA1 account. We are a technology platform, not a bank, brokerage, or custodian.Your brokerage credentials remain protected. ALGORA1 never asks for or receives your brokerage password. Connections are established through your brokerage's authorized integration or a third-party connectivity provider. Any access credential required to maintain the connection is encrypted and stored securely, never exposed in your browser, and deleted when you disconnect your account.You remain in control of your account. ALGORA1 can read account information and submit trading orders only after you authorize a brokerage connection. You can configure trading limits, switch to review mode to approve orders individually, halt automated trading, or disconnect your brokerage at any time.Your assets remain with your brokerage. Every order is submitted to your connected brokerage, which independently accepts, rejects, executes, and clears transactions. ALGORA1 never takes possession of the cash or securities involved.Security and privacy matter. We use encryption in transit, encrypted storage for brokerage access credentials, and restricted access controls to protect sensitive information. We do not sell your personal data or collect your Social Security number or bank account details.An important distinction: While ALGORA1 does not custody your money, automated trading involves real financial risk. Orders placed through your authorized connection can result in losses, including the loss of invested capital. No software or security measure can eliminate all risks associated with trading, technology, or unauthorized access.

Every backtest runs on real market history, after trading costs and regulatory fees. The strategies our research desk publishes go much further. Each one has to get through the kind of review an institutional quant team would run, and nearly every idea fails it.Real-world costs and fills. Every round trip pays the stock’s own measured bid-ask spread, never less than 2 basis points or half a cent a share a side at the price it traded at back then. On top of that come SEC and FINRA fees on every sale. Signals are calculated after the close and filled at the next trading day’s open, never at the closing price they came from.Total return, measured like a fund. Dividends are credited as they’re paid, uninvested cash earns the Treasury-bill rate, and Sharpe and Sortino ratios are measured against T-bills.Only what was knowable at the time. Earnings dates and financials are dated to when they were filed with the SEC, and short interest to when FINRA published it. Renamed companies keep their full history. Tests reach back as far as 2003, up to 23 years, and never cover less than 10.No survivorship bias. Each strategy is also run on up to 40 similar companies that were delisted during its test, and it’s refused if it lost money on them.A bar that rises with every idea tested. Test enough rules and a few will look brilliant by luck. So the desk counts every strategy it has ever tried and raises its bar to match. A strategy needs a t-statistic above 3.5 twice: once on its own trades, and again with its delisted look-alikes added in. That’s stricter than the 3.0 Harvey, Liu and Zhu proposed for new findings in finance.A report a professional would recognize. Every published strategy shows:its deflated and probabilistic Sharpe ratios, CVaR, Omega, Ulcer index and conditional drawdown at riskits rolling 12-month Sharpe, factor-adjusted alpha and after-tax returnits capacity and the trading cost it could absorbits correlation with every other published strategyPortfolios answer to their own tests. Their weights are fitted on the earlier years with shrinkage estimators (Ledoit–Wolf for risk, James–Stein for returns). They’re then judged only on the years held back. There a portfolio needs a Sharpe ratio of at least 1.0, an average correlation of 0.6 or less between members, and better results than its own members.Results are still hypothetical. No backtest captures every real-world detail, such as partial fills or the price impact of very large orders, and past performance doesn’t predict future returns.

Our network learns from every trading day in the history of the roughly 500 largest U.S. companies since 2004: more than 2 million company-days. For each company and each day it weighs 75 measurements across 11 kinds of data: how the stock has traded over short and long horizons, its risk and volume, the market conditions around it, earnings timing, intraday trading, fundamentals from financial statements, SEC filings, news and the moves of its industry peers.Its forecast is the average of an ensemble of networks trained independently, and the process around it is built so it can't flatter itself:It only uses what was knowable at the time. Every input is dated to when it became public.It's tested on years it never saw. We rebuild it year by year since 2009, each time from the years before, and judge it on what happened next.It had to earn its place. Before choosing it, we trained four rival versions, one of them on virtually the entire U.S. stock market: more than 14,000 companies and more than 25 million company-days, including companies that failed, such as Lehman Brothers and Silicon Valley Bank. Every version was judged under rules we fixed before seeing any results. The one in use won that contest, then passed a final test on years held back for it.Testing this generation took cloud machines with nearly 200 virtual processors and almost 4 terabytes of memory between them.

Real-time prices come from the consolidated feed of every U.S. exchange. Charts and backtests use more than 20 years of daily history, adjusted for splits, with dividends counted. Company financials, insider trades and 8-K events come from SEC filings, each dated to when it was filed.

No. You can describe a strategy in plain English and have it built and backtested for you on Basic and Premium. You can also start from one of the research desk’s published strategies, or import a script you already have in Pine Script, thinkScript, EasyLanguage, NinjaScript or Python.