MapleRESEARCH
Back to mapleresearch.ca
Frequently asked questions about Maple Research: what it's building, whether it gives financial advice, how it differs from a backtester or a terminal, and how to follow along before launch.
Maple Research is building institutional-grade infrastructure for financial research, simulation, and validation — designed to help someone move a financial hypothesis from data to evidence, rather than another single-purpose backtesting tool.
Same company, broader scope. The earlier version of Maple focused primarily on helping algorithmic traders backtest and validate trading strategies. That prototype isn't being presented as the current product — the lessons from building it are shaping the broader research infrastructure now in development. Validation, the strongest part of the original product, remains central.
No, and it isn't trying to be. Charting platforms are optimized for visualization and trading workflows; terminals are deep data and analytics platforms; Maple is not attempting to replace either. It's aimed at the layer where fragmented data and models get turned into reproducible research evidence — the connective tissue those categories don't provide, not a replacement for them.
No, none of those. Maple is research and decision-support infrastructure. Nothing it's designed to produce — a test result, a validation read, or AI-assisted commentary — is a recommendation to buy, sell, or hold any asset, and it is not designed to place trades or connect to a brokerage.
No. Maple makes no promise of profit, accuracy, or future performance. Results are hypothetical and simulated; past or simulated performance does not guarantee or indicate future results.
Backtesting is running a set of rules against historical data to see how they would have performed. It's one input Maple is designed to produce, not the destination — a historical result is treated as one piece of evidence, subject to the validation concepts described in Methodology, not a conclusion on its own.
Overfitting happens when an idea is tuned so precisely to a specific historical dataset that it captures noise rather than a real, repeatable pattern — producing a result that looks excellent but fails to hold up on new data. Maple's validation concepts are specifically designed to catch signs of this before anyone puts weight on a result.
Yes, in a deliberately bounded way: AI is designed to help express a hypothesis (turning a plain-English idea into structured logic) and to help explain a result in plain language. The underlying calculations are designed to come from a deterministic engine, not from the AI model itself — AI assists with expression, it doesn't decide what a result is.
Not yet — Maple is in active development, and this site is intentionally not a finished storefront. There's no account creation, no pricing, and no dashboard to use today. The way to follow along is to join the waitlist.
Join the waitlist with your name, email, and role. There's no account and no password required — it's a plain expression of interest so Maple can reach you as the platform comes together.