Public page collection

Strategy research guides: published pages

Browse the published Strategy research guides collection with direct links and numbered pages.

Published pages
41
Directory page
1 of 1

Pages 1–41

ChatGPT as a trading agent: dividends, tested | NexusTrade

An experiment in using ChatGPT beyond chat. Research dividend growers, test a five-company allocation, and compare both recorded periods with SPY.

Open page

Claude.ai as a trading agent: SPY spread, tested | NexusTrade

An experiment in using Claude.ai beyond chat. Research a SPY bull call spread, build three explicit rules, and inspect the completed 2024 test at 26.49% against SPY.

Open page

Claude Code as a trading agent: GOOG trend, tested | NexusTrade

An experiment in using Claude Code beyond coding. Research GOOG, build 50/200-day trend rules, backtest four windows including a 6.01% loss, then review paper and live deployment.

Open page

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

Cursor as a trading agent: PLTR RSI draft | NexusTrade

An experiment in using Cursor beyond coding. Research Palantir, preview RSI recovery rules, and prepare the first historical test.

Open page

Dots as a trading agent: BTC trend, tested | NexusTrade

An experiment in using Dots beyond chat. Research BTC-USD, test a 50-day trend rule, and inspect the completed 2024 run against SPY and BTC.

Open page

Gemini CLI as a trading agent: TSLA breakout draft | NexusTrade

An experiment in using Gemini CLI beyond coding. Research Tesla, preview volatility breakout rules, and prepare the first historical test.

Open page

Grok Bot as a trading agent: SOL momentum, tested | NexusTrade

An experiment in using Grok Bot beyond chat. Research SOL-USD and inspect the completed 2024 test, which lost 5.18% against SPY.

Open page

From a trading idea to a live portfolio | NexusTrade

Follow one GOOG strategy through research, rule creation, backtesting, paper observation and a reviewed live deployment.

Open page

Deploy a reviewed strategy to live trading | NexusTrade

See broker selection, account review, strategy changes, evaluation timing, order approval and pausing in NexusTrade.

Open page

Meta Muse as a trading agent: ETH mean reversion | NexusTrade

An experiment in using Meta Muse beyond chat. Research ETH-USD and inspect the completed 2024 test, which lost 9.42% against SPY.

Open page

Copilot as a trading agent: SPY put spread, tested | NexusTrade

An experiment in using Copilot beyond code. Research a SPY bear put spread and inspect the completed 2024 test, which lost 13.34% against SPY.

Open page

NexusTrade vs AInvest: a real SPY simulation, research sources and rule fidelity | NexusTrade

Inspect AInvest's executed SPY simulation and 50% cash variant, compare an observed NexusTrade request mismatch, and trace Apple filing facts into testable strategy rules.

Open page

NexusTrade vs StockHero: order sizing, paper tests and fill-state rules

Compare StockHero base and extra orders with NexusTrade order-state rules. Work through $10,000 sizing, advanced bot conditions, historical testing and paper evidence before choosing a platform.

Open page

NexusTrade vs Tickeron: Inspect a vendor's robot, or test the exact rules you own | NexusTrade

Compare Tickeron's AI robot logs with your own editable NexusTrade strategy. Work through actual annualized-return arithmetic and a completed SPY option entry.

Open page

NexusTrade vs Tradetron: option replay and decision evidence

Compare historical option backtests, minute evaluation, previous-trade state and MCP research workflows in NexusTrade and Tradetron. Inspect a completed option example and the actual audit contracts.

Open page

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

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

AI trading agent safeguards: stop the next trade before a bug compounds

Watch an order wait for approval, trace a buy/sell loop through its events, and see a daily allowance stop further automatic trades in NexusTrade.

Open page

Does copying Congress beat SPY, and does entry timing matter?

We tested congressional stock purchases against SPY and compared entry before and after disclosure. Explore both findings, the uncertainty, and results by politician and disclosure delay.

Open page

Are news headlines enough for stock sentiment analysis?

Our broad GDELT audit exposed missed parent companies, conflicting model scores and faulty labels. Here is what article text might fix and what needs a separate repair.

Open page

Does news sentiment predict stock returns? Results across five horizons

We tested 2.27 million company days across the next session, week, month, quarter and year. See the return gaps, uncertainty, missing outcomes and the next hypothesis.

Open page

Stock news sentiment analysis: fine-tuning a cross-encoder for trading

Fine-tuned DeBERTa agreed with reference labels on 87.9% of 434 company validation examples, versus 74.5% for frozen Qwen embeddings. I scored 67.8M target pairs; trading results are next.

Open page

A news classifier can be 96% accurate and miss most relevant stories

Our GDELT probe reached 95.90% overall ticker-array agreement while matching only 7 of 20 relevant headlines. The denominator explains the difference.

Open page

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

XGBoost vs neural networks for sentiment analysis: which is better?

I compared XGBoost with a small neural network on the same financial headlines and embeddings. The MLP had 10.4% lower sentiment error at the largest training size.

Open page

Backtest data sources and pricing checks | NexusTrade

Follow a recorded SPY option decision and fill, inspect Massive’s documented exchange feeds, and check quote timing and historical holdings availability.

Open page

How Do Congressional Stock Trade Disclosures Work?

How NexusTrade turns House and Senate trade reports into dated rows, the PoliticalTrades indicator and copy-trading bots, and how often each updates.

Open page

Does LLM Hindsight Change News Sentiment Scores? | NexusTrade

I scored 10 famous stock headlines and summaries with Claude Haiku 5.5, as written and with the company masked. The mean masking gap (0.15) beat mean rerun noise (0.10), and masking also deleted information, so the result is inconclusive.

Open page

Point-in-time universes: dated membership and dividends | NexusTrade

Audit historical stock eligibility with Tesla's dated S&P 500 addition, Target dividend announcements, and a reproducible worksheet for the five-dividend-growers study.

Open page

Create a strategy from congressional trading disclosures | NexusTrade

Use publicly disclosed congressional purchases as a trading signal with explicit member, instrument and trailing-window scope.

Open page

Create a strategy using economic indicators | NexusTrade

Use macroeconomic conditions in strategy rules, inspect units and releases, and compare fixed regime thresholds.

Open page

Create a strategy using fundamental indicators | NexusTrade

Build trading rules from reported company metrics, inspect the source period and test clear entry and exit conditions.

Open page

Create a strategy from insider trading disclosures | NexusTrade

Build rules from disclosed insider purchases, specify officer or director scope and inspect the filing behind each signal.

Open page

Create a strategy from institutional holdings | NexusTrade

Use public Form 13F holdings changes, select manager scope and inspect successive disclosed quarters.

Open page

Why a profitable backtest can still fail | NexusTrade

A real NVDA strategy earned 22.06% in a later simulation and failed 4 of 5 checks. See what changed in its rules and review the experiment in Aurora.

Open page

Create a strategy with mixed indicators | NexusTrade

Combine price trends and company metrics, define complementary exits and compare each component with the combined rule.

Open page

Test a frozen trading strategy on later dates | NexusTrade

Plan a later test of your own unchanged strategy. Follow the completed NVDA case to see why return, exits, costs and predeclared requirements need separate review.

Open page

Move a tested strategy from paper trading to live trading | NexusTrade

Deploy a saved paper portfolio, observe signals and orders, then review the exact broker target and automation settings before live trading.

Open page

Create, optimize and check a trading strategy | NexusTrade

Start with a complete entry, exit and size. Choose a first rule preview, a recorded optimization example or a later-test plan.

Open page

Create a strategy using technical indicators | NexusTrade

Turn price, moving averages and oscillators into explicit trading rules, test variants and inspect recorded signals.

Open page

Continue browsing

All public collections ↗