Public collection search

Search the research library

Find guides, stocks, ownership disclosures, public portfolios, creators and research studies.

Results for “Walk-forward”

36 matching pages · Page 1 of 1

Trading case studies

Walk-forward optimization: a retrospective TQQQ research loop

Three rounds of TQQQ variants, losing-trade inspections and rule repairs, followed by five walk-forward blocks. Compare matched-fold and continuous holding, inspect weaker periods and see which development dates overlap the tests.

Open page
Articles, videos and guides

Claude Fable 5 built me a live options strategy. It DESTROYED the market out of sample. Then the government banned it.

Claude Fable 5, the strongest finance model ever measured, built a momentum-LEAP options strategy through a public walk-forward runbook. It beat the market by more than ten to one out of sample, and I deployed it live on my $25,000 public account. Three days into the model's life, the US government placed it under export controls and Anthropic took it offline. The full runbook, agent trace, and live book are open.

Open page
Strategy research guides

Codex as a trading agent: NVDA momentum, audited | NexusTrade

An experiment in using Codex beyond coding. Research NVDA, freeze intraday rules, and inspect walk-forward selection, fee sensitivity, and a trade audit.

Open page
Trading case studies

NVDA intraday strategy vs buy and hold: a case study | NexusTrade

An NVDA intraday strategy led in a nine-month replay, then lagged buy and hold over five folds. Inspect its rules, walk-forward tests, costs and 212 audited fills.

Open page
Walk forward optimization

Walk-forward optimization: five real NVDA selections | NexusTrade

See how a real strategy chose its settings five times, then tested each version on later prices. Explore the rules, dates and results, or open the complete example in Aurora.

Open page
Walk-forward studies

Public Portfolio Challenge walk-forward

Walk-forward studies

Open page
Walk-forward studies

Pelosi disclosures walk-forward optimization

Walk-forward studies

Open page
Articles, videos and guides

videos?topic=walk forward testing

Articles, videos and guides

Open page
Public portfolios

Pelosi Disclosures: Walk-Forward Winner (paper) public portfolio

Holds the stocks Nancy Pelosi disclosed buying in the last 90 days, weighted by the high end of each disclosed dollar range, fully invested. These settings won

Open page
Articles, videos and guides

Introducing the new NexusTrade, the world's first agentic trading marketplace

Robinhood built an AI agent that can barely trade. I built a market where you can sell yours. Copy a real deployed trading bot with a public track record, or describe your idea to Aurora and let its 84 tools research, build, backtest, and validate it. List your own bot and keep up to 95% of every subscription, paid through Stripe. No code required. The app store of AI trading bots is open.

Open page
Articles, videos and guides

How to Design an Algorithmic Trading System: Junior to Senior

Design an algorithmic trading system from a junior-level MVP through a mid-level production service to a senior-level, fault-tolerant trading platform.

Open page
Trading case studies

Trading strategy case studies: rules, returns and drawdowns | NexusTrade

Inspect real strategy experiments, the published ideas behind them, actual trade diagnostics, matched controls and the changes that helped or failed.

Open page
Articles, videos and guides

Moderna basically cured cancer, so I used Grok Bot to create a trading strategy on it. It's DESTROYING the market.

I connected xAI's Grok Bot to NexusTrade, funded a $13,500 Public account, rejected its sector-gated design, and rebuilt it around 26 company-level theses. The replacement passed 4 of 5 out-of-sample folds with a 22.47% worst OOS drawdown and is now live with manual order approval.

Open page
Articles, videos and guides

I just tried Robinhood's alleged "Agentic Trading". I am not impressed.

I built a full Robinhood integration for NexusTrade, live-tested every MCP response shape, and un-shipped it because OAuth only completes on localhost. No crypto, no debit spreads, no documentation, and production connect hits /oauth/error.

Open page
Selection bias

Selection bias in strategy research: keep the losers in the record | NexusTrade

The same dividend strategy beats its stored SPY baseline in one period and trails it in another. Follow both actual curves before choosing which result to share.

Open page
Articles, videos and guides

I turned $5,199 into $21,935 betting on Google. Then OpenAI took over my trading platform. I sold every call.

After 14 months as a Google fanboy, 185,172 production requests and $2,129 of inference spend moved OpenAI's budget model onto the high-volume jobs inside my trading platform. Google kept screening. I sold every Google call I owned.

Open page
Grok bot trading

How to connect Grok Bot to NexusTrade | NexusTrade

Connect Grok Bot to NexusTrade, verify the account with a read-only check, then inspect a dated NVDA company example. Includes the original Bot setup image.

Open page
Lookahead bias

Lookahead bias: audit signals, filings and historical fills | NexusTrade

Follow one decision made before its input existed. Compare the early and corrected timelines, then ask Aurora to check the exact timestamps.

Open page
Articles, videos and guides

This strategy has beaten the market for over 5 years. Here’s how I created it.

Articles, videos and guides

Open page
Developer guides hub

How to Build an LLM Judge Training Dataset for AI Agents | NexusTrade

I built 889 graded AI agent decisions to fine-tune an LLM judge. An AI checker flipped 12 of 29 grades, so I used blind review. Here is the method and the training plan.

Open page
Composer comparison

NexusTrade vs Composer: saved rules, symphonies and automation

Compare NexusTrade and Composer for minute-level backtests, option strategy replay, fill-state rules and an inspectable research workflow. Examine saved rules and concrete sizing first.

Open page
Out of sample testing

Out-of-sample testing: inspect a frozen NVDA strategy | NexusTrade

Completed NVDA experiment: a frozen searched strategy gained 22.06% on later dates, held overnight and failed four of its five daytrading requirements.

Open page
Portfolio risk indicators

Portfolio risk indicators: read the path behind the return | NexusTrade

Follow a $3,500 holding inside a $10,000 account. See the concentration, check the proposed cap, and ask Aurora to explain the exact sizing before changing a rule.

Open page
Strategy research guides

NexusTrade vs TradingView: backtests, rules and research | NexusTrade

Compare a Pine Script entry-cooldown example with NexusTrade fill-state rules, intraday and options research, recorded trade evidence, and external AI-client workflows.

Open page
Strategy research guides

NexusTrade vs TrendSpider: backtests, rules and research | NexusTrade

Compare TrendSpider one-minute Strategy Tester and Sidekick with NexusTrade portfolio rules, contract-selection backtests, external clients and inspectable research evidence.

Open page
Trading case studies

Can a dividend portfolio beat the market? | NexusTrade

The published five-stock dividend portfolio beat matched SPY recently. New concentrated rules improved earlier growth but lost that recent comparison.

Open page
Articles, videos and guides

My AI bought a stock it shouldn't have. Then I couldn't get rid of it.

A bad price tick fired a META signal that should never have existed. The fill landed at the open. The UI didn't know how to close the spread. Three hours later, sixteen commits, and one stateless Rust risk engine that gates every close path on the platform.

Open page
Claude ai paper trading

How to paper trade with Claude | NexusTrade

Preview this exact candidate, review a separate Paper deployment, then inspect and pause the running book.

Open page
Vscode paper trading

How to paper trade with VS Code Copilot | NexusTrade

Preview this exact candidate, review a separate Paper deployment, then inspect and pause the running book.

Open page
Chatgpt paper trading

How to paper trade with ChatGPT | NexusTrade

Preview this exact candidate, review a separate Paper deployment, then inspect and pause the running book.

Open page
Articles, videos and guides

I was laid off from my job where I made over $400,000/year. Here’s why I’m not upset.

Articles, videos and guides

Open page
Codex trading

Research and test trading strategies with Codex | NexusTrade

See Codex validate a dividend-growth strategy, run a historical backtest and compare the completed curve with SPY. Copy the exact rules to try the workflow.

Open page
Articles, videos and guides

Deployment: From Paper Trading to Going Live — Algorithmic Trading Fundamentals

The hardest part of algorithmic trading isn't building the strategy — it's deploying it with real money. Learn the paper trading framework, live trading toggle, and signs a strategy isn't ready to go live.

Open page
Articles, videos and guides

I went to the BEST school in the world for Artificial Intelligence. Here’s how I’m using this to help everyday retail investors

Articles, videos and guides

Open page
Strategy research guides

Can news sentiment improve a top 10 stocks strategy?

I filtered the 10 largest US companies by 60 sessions of news sentiment. The worst drawdown fell from 41.4% to 31.6%, yet holding the top 20 with no news did better, and news on the top 20 cut its return.

Open page
Public conversations and agents

Point-In-Time Top Five Equity Study

The full research trace: nine point-in-time top-5 equity candidates plus an SPY control, backtested over 2020-2026, swept across 786 evaluations, and taken to a six-fold walk-forward study that rejected the leading candidate.

Open page

More results

Browse public collections ↗

Continue exploring

Browse every public collection ↗Explore guides and starting points ↗