Automated and quantitative approaches, and where machine reading of a market helps or misleads.
132 articles in this section of the Journal, grouped by topic. Every one is free to read.
AI in Trading 24
- What You Can Actually Ask Dr. NoVo, the Markets SIIt looks things up in the live map before answering and names what it used, which changes the kind of question worth asking.
- AI Trading Risks & LimitationsAI trading carries real risks: overfit models, silent failures, over-trust, regime change, and tech faults. Automation removes emotional error, not market risk.
- AI Trading vs Human TradersAI beats humans at speed, consistency, and emotional control. Humans beat AI at context, judgment, and adapting to novelty. The best setups pair the two. Here's the.
- AI vs a Rules EngineA rules engine follows fixed if-then logic; an AI layer interprets context. Here is how they differ in trading, why the best systems combine both, and where each.
- Can AI Predict the Stock Market?Can AI predict the stock market? Not in the way people hope. Markets are near-random and adversarial. What AI can do is estimate probabilities and react — not.
- Can a Vision Model Read a Chart?Modern vision-capable AI models can interpret chart images — but what does that actually add to trading beyond the raw numbers? Here is what vision reads, where it.
- Does AI Trading Actually Work?Does AI trading work? Honestly: it depends on what you mean by 'work.' AI reliably removes emotional error and executes consistently.
- How Does AI Trading Work?AI trading works as a pipeline: ingest market data, turn it into features, run a model, apply rules and risk limits, then execute. Here is each stage in plain terms.
- How to Spot an AI Trading ScamAI trading scams share the same tells: guaranteed returns, custody of your money, hidden logic, and fake track records. Here are seven red flags that should make.
- Is AI Trading Profitable?AI trading is not automatically profitable. Profit comes from a real edge, disciplined risk sizing, and low costs — the AI just executes them. Here's what actually.
- LLMs in the Trading LoopLarge language models are powerful at synthesis and explanation but wrong for millisecond execution. Here is exactly where an LLM belongs in a trading system — and.
- Machine Learning in TradingMachine learning in trading means training a model on historical data to recognize patterns in features like volatility and order flow. Here's how it works — and.
- Neural Networks for TradingNeural networks find complex patterns in market data that simpler models miss — but that same flexibility makes them overfit and act as black boxes. Here's the.
- Reinforcement Learning in TradingReinforcement learning trains an agent to act by rewarding good outcomes. In trading it's promising for execution and sizing, but reward design and non-stationary.
- Sentiment Analysis in TradingSentiment analysis uses NLP to score the mood of news and social posts. It can add context, but it's noisy, laggy, and easily gamed. Here's how it's used and where.
- What Is AI Trading?AI trading uses machine models to read market data and drive decisions or execution. Here is what it actually is, what it is not, and where the real value sits — in.
- Why AI Needs GuardrailsAn AI that can place trades without hard limits is a liability, not an asset. Here is why guardrails — risk caps, deterministic gates, human-set boundaries — are.
- Why a Raw LLM Can't TradeAsking ChatGPT to 'trade for me' fails for concrete reasons: no real-time data, no execution, latency, non-determinism, and no risk controls. Here is why an LLM is.
- A Markets SI for Someone New to OptionsWhat a markets SI gives a beginner, the order to ask things in, and the three things it will never do for someone who is new.
- A Markets SI for an Experienced Trader: What It SavesThe sweep across markets, the hours nobody watches, the exceptions and the gaps. What a markets SI takes off an experienced trader’s plate.
- One Week With a Markets SI: A Diary in Plain EntriesSunday to Saturday in short entries: the question asked, the shape of the answer, and what was left to the trader.
- The Midday Check: Three Minutes With a Markets SIThree questions at midday: the side of the flip, the share of the expected move used, and what is old or missing.
- Writing Down What a Markets SI Told YouFive fields to note from each answer, and why the notes are about your decisions and not about the SI.
- A Push Arrives: What to Ask a Markets SI NextTwo pushes, three questions each. What to ask a markets SI in the minute after your phone buzzes.
Algo Trading 101 13
- Algo Trading vs Day TradingDay trading is a style (in and out same day); algo trading is a method (software executes the rules).
- Algorithmic Trading StrategiesThe main algorithmic trading strategy types — trend following, mean reversion, breakout, momentum, and market making — explained simply, with what conditions each.
- Algorithmic Trading for BeginnersA beginner's primer on algorithmic trading: what it is, the myths, what you actually need, and the realistic path in. No hype — just what a new automated trader.
- Backtesting 101Backtesting runs a strategy against historical data to estimate how it would have performed. Done right it's invaluable; done wrong it's a lie generator. Here are.
- Can You Make a Living Algo Trading?Can you make a living algo trading? Some do, most don't, and it depends on capital, a real edge, and treating it as a business, not a lottery ticket. Here's the.
- Common Algo Trading MistakesThe mistakes that sink new algo traders: overfitting, ignoring costs, oversizing, no fail-safes, and blind trust. Each is avoidable once you know it. Here are the.
- Do Trading Bots Really Work?Trading bots 'work' at what they're built for — executing rules tirelessly and without emotion. They don't work as money-printers.
- Do You Need to Code to Algo Trade?You don't strictly need to code to algo trade — no-code platforms and turnkey systems exist.
- How Much to Start Algo Trading?You can start algo trading with a few hundred dollars, but how much you need depends on the instrument, position sizing, and surviving variance — not a magic number.
- How to Start Algorithmic TradingStarting algorithmic trading: pick a broker with an API, define a simple rules-based strategy, backtest it honestly, paper trade it, then go live tiny. Here's the.
- Overfitting in TradingOverfitting is when a strategy is tuned so tightly to past data it memorizes noise and fails live. It's the #1 reason great backtests lose real money. Here's how to.
- What Is Quantitative Trading? Quant Trading Explained (2026)Quantitative trading means deciding from data and math, not gut feel. Here's what 'quant' really means in 2026, how it differs from algo…
- What Is an Automated Trading System?An automated trading system executes entries, exits, sizing, and risk by rules through a broker API — no human clicking. Here are its parts, and what separates a.
The System 13
- Automation Isn't PassiveAutomated trading removes the manual work of execution, but not the responsibility. It still needs monitoring, sane risk boundaries, and an operator who…
- Backtest vs Forward-TestA backtest shows how a strategy would have done on past data; a forward-test shows how it does on new, live data.
- Conviction-Based SizingConviction-based sizing scales position size with the quality of a setup — larger on the strongest signals, smaller on marginal ones
- Flat at the CloseAn intraday system flattens every position before the bell to avoid overnight gap risk and, for 0DTE, the total loss of holding to expiration.
- Hosted vs Self-HostedSelf-hosted automation runs on your own machine — full control, but it must stay on and maintained.
- Kill Switches & Fail-SafesAn automated system that can't be stopped or that keeps trading through a malfunction is a hazard. Here is why kill switches and fail-safes are mandatory, and what.
- Look-Ahead BiasLook-ahead bias is when a backtest accidentally uses information that wouldn't have been available at decision time
- Manual vs Automated Execution: The Consistency GapThe real difference between a manual trader and an automated system isn't intelligence — it's consistency.
- Setting Risk BoundariesA non-discretionary system executes within boundaries you set: the instrument's risk profile, position sizing, stops, and exposure caps.
- Survivorship BiasIf your backtest only includes stocks that still exist today, it's ignoring every company that failed — and its results are a lie. Here is how survivorship bias.
- Walk-Forward OptimizationWalk-forward optimization tests a strategy by tuning it on one slice of data and validating on the next unseen slice, rolling forward
- What NoVo Actually IsNoVo maps dealer positioning on SPY, QQQ & IWM options and tells you what that structure has tended to mean. Here's the.
- Who Holds Your Money?In safe automated trading, you hold your own money — the software connects to your broker via API and can trade but never withdraw.
Trading Infrastructure 15
- A Resilient Trading LoopThe real test of a trading system isn't the happy path — it's what happens when the data feed drops, the broker times out, or a quote goes stale. Here is what.
- Alpaca vs Tradier for OptionsAlpaca and Tradier are two popular API-first brokers, but they serve different roles for an options trader. Here is how they compare on options access, paper.
- Broker API Rate LimitsEvery broker API caps how many requests you can send per second. Ignore it and your orders get throttled or rejected at the worst time. Here is how rate limits work.
- Event Loops in Trading SystemsReal-time trading systems are built on asynchronous event loops so they can react the instant data arrives instead of waiting in line. Here is what that means and.
- How Options Orders Get RoutedBetween clicking 'buy' and getting filled, your options order travels through a routing chain most traders never see. Here is the path — broker, router, exchange.
- Idempotency in Order SubmissionWhen a network hiccup leaves an order's status unknown, a naive retry can submit it twice.
- In-Memory State in TradingFast trading systems keep their live state in memory (RAM), not on disk, so reads and writes happen in microseconds. Here is why disk is too slow for the trading.
- Latency in Retail TradingLatency — the delay between a decision and its execution — quietly erodes short-term trading edges.
- Polling vs Streaming DataA trading system can pull market data on a timer (polling) or receive it pushed in real time (streaming).
- A Feed That Stops Versus a Market That Is QuietUnchanged because nothing traded, or unchanged because the pipe broke. Two timestamps tell them apart.
- One Source of Truth for a Number Shown in Several PlacesWhy copies of a calculation drift, what computing it once buys, and which things must stay separate numbers anyway.
- Time Zones, Daylight Saving and the Cash Close as an AnchorExchange time, UTC and the reader’s own clock, what daylight saving does to all three, and why the cash close makes a good fixed point.
- What a Heartbeat Is ForA scheduled signal that says a system is alive, so that silence stops being ambiguous. How it works and what it should be attached to.
- Two Timestamps: When It Happened and When You HeardEvent time and arrival time, why either one alone misleads, and what to say when the source gives no time of its own.
- How a Candle Is Built, and What a 15-Minute Bar Cannot SeeFour prices from many trades. Where the interval’s edges fall, the bar that is still forming, and the interval with no trades in it.
Quantitative Trading 14
- Attribution: Finding Out Which Setup Actually PaysAttribution means tagging every trade with why you took it, then measuring each setup separately. It is how you find out which plays make money and which merely
- Data Mining Bias: Torture the Data and It ConfessesData mining bias is what happens when you test many ideas against one dataset: something always looks great by chance. Here is why it happens and how to defend
- Expectancy: The Only Number That Says a Strategy WorksExpectancy is (win rate x average win) - (loss rate x average loss). It is the only number that says whether a trading strategy makes money. Here is how to comp
- How Many Trades Before You Believe It?A handful of trades proves nothing. Here is why small samples lie, roughly how many trades you need before a result means something, and how to think about it w
- Monte Carlo: Stress-Testing a System Before the Market DoesMonte Carlo simulation reshuffles your trade history thousands of times to reveal the drawdowns and outcomes you could plausibly face. Here is how it works and
- Transaction Costs: Where Most Edges Quietly DieMost strategies that look profitable on paper are killed by costs: commissions, the bid-ask spread, and slippage. Here is how to account for them before they ac
- Variance vs Edge: Why Good Systems Have Bad WeeksVariance is the noise around your edge. It guarantees losing streaks in profitable systems. Here is how to tell a drawdown from a dead strategy before you break
- In-Sample Versus Out-of-Sample: The Data You Tuned On and the Data You Did NotThe data used to build a rule and the data held back from it, and the quiet ways the second gets spoiled.
- A Market With No History Cannot Be BacktestedNew perps and tokens have no past to test against. What can be done instead: describe, record, and label the span honestly.
- Regime Change: Why Old Statistics Stop ApplyingAn average carries the conditions of its sample. When the regime moves, the number stays accurate about the past and stops describing the present.
- Mean Versus Median: Which Average a Lopsided Market NeedsTwo averages that disagree whenever a few values are enormous. When each one is the right summary, and what the gap between them says.
- The List You See Is the Survivors: Survivorship in Tokens and StocksEvery list has an entry rule, and the rule is the bias. With new tokens, what the list leaves out is almost everything.
- Measuring Something Versus Predicting ItWhat is versus what is expected: how each kind of number is made, how each fails, and the verb that turns one into the other.
- A Percent Change Needs a Base and a WindowUp from what, and since when. The base, the window, and what happens when the record is shorter than the label claims.
Signals vs Systems 14
- Automated Tool ChecklistJudge an automated trading tool by its architecture, not its equity curve: non-custodial, transparent risk controls you set, a real stop and kill switch, honest.
- Black-Box vs TransparentA black-box bot hides what it does and why; a transparent system lets you see and set the rules acting on your money. When you can't inspect the logic, you can't.
- Copy Trading vs Your Own RulesCopy trading mirrors someone else's trades into your account — outsourcing judgment to a stranger.
- Managed vs Non-CustodialA managed account hands your money to someone else to trade; non-custodial automation runs in your own broker account via API, so you always hold the funds. The.
- Signal vs Fill: The GapA signal tells you what to do; a fill is you actually doing it. Between the two sit lag, hesitation, sizing, and emotion
- Why Signal Groups DisappointSignal groups disappoint for structural reasons: lag, no risk management, one-size-fits-all calls, cherry-picked records, and misaligned incentives.
- Why Trading Bots Blow UpTrading bots rarely blow up because their signal was wrong — they blow up from the missing risk layer: no position limits, no stops, no fail-safes, and…
- A Signal Is a Moment. A System Is a Routine.A signal answers one question and stops. A system is the whole loop: what qualifies, how much, where you are wrong, when you do nothing.
- Why an Alert Is Not a TradeA message that a condition became true, late by design. What a trade needs that an alert never carries, and what to do when one fires.
- The Context a Signal LacksWhere price is, what time it is, how big the move is for this market, who is behind it, and what you already hold.
- A Readout Versus a RecommendationWhat is happening versus what to do about it. How one drifts into the other a clause at a time, and three checks for telling which you are reading.
- Rules You Write Before the OpenIf-then rules chosen with nothing on: what qualifies, how much, where you are wrong, when to stop, and when to do nothing.
- What a System Does When the Data Is MissingAbsent, stale or untrustworthy: three kinds of missing, three bad defaults, and the short rule that replaces them.
- A System Needs a Way to Do NothingThe idle state, defined as carefully as the active one: when to stand aside, why it is hard, and what forcing a trade costs.
AI & Market Analysis 38
- The Future of AI in Market AnalysisWhere AI market analysis goes next: from dashboards you read to analysis you interrogate, grounded answers over confident ones, and why the edge shifts to.
- What an AI Market Analyst Actually DoesAn AI market analyst reads structure and explains it. Here is the concrete job - what it reads, what it can answer, and the three things it should never be asked.
- Where AI Has a Real Edge in Market AnalysisThe AI edge in market analysis is not prediction. It is coverage, memory, consistency and translation - four advantages that are real, measurable, and easy to.
- What a Markets Super Intelligence Reads on a SundayOn a Sunday the cash market is shut and a great deal is still trading. What a markets SI reads then, and where it stops.
- SI Versus AI: What Changes Besides the WordThe government changed a word and no software improved. What SI can mean for a trader, and the limits that stay put under either name.
- What Makes an SI a Markets SI: Coverage, Hours, RestraintThree things separate a markets SI from a general one: how much it reads, when it reads, and where it stops.
- A Markets SI Versus a Human Desk: Where Each Is BetterBreadth, hours and sameness on one side. Context, responsibility and judgment on the other. A specific comparison, with no winner declared.
- Reading Every Venue That Is Open, Including the Ones That Never CloseVenues with a bell, venues without one and venues that half close. What a markets SI can read from each, hour by hour.
- Why a Markets SI Says How Old Every Number IsProse hides the timestamp a dashboard would show. Why an SI states the age of each figure, and the ages that look alike but are not.
- Why a Markets SI Refuses to ForecastDeclining the question everyone asks is what keeps the other answers clean. What a reading is, and what a forecast would cost.
- An SI That Says It Does Not Have That, Versus One That GuessesSome numbers exist nowhere. What a good refusal contains, and why a guess is the most dangerous answer a markets SI can give.
- How to Ask a Markets SI a Good QuestionName the instrument and the venue, ask about now, ask for the comparison and the age. Four habits that turn a vague question into a reading.
- Five Questions Worth Asking a Markets SI Before the OpenThe perps against the close, the names carrying them, the flip and walls, the expected move, and what the SI is missing this morning.
- Questions a Markets SI Should RefuseFive questions a markets SI should turn down, the reason for each, and the readable question hiding underneath.
- Reading Two Books at Once: Equities and CryptoEquity structure and crypto structure are read differently. What a markets SI takes from each, where they now touch, and what does not carry over.
- What a Markets SI Adds to a Dealer MapThe map draws the levels. The SI says how they relate, reads three indexes together, and states what the map cannot tell you.
- What a Markets SI Adds to a List of Trending CoinsA trending list ranks attention. The SI adds the pool depth, the contract behind the name, and which entries are there for the first time.
- What a Markets SI Says When a Feed StopsAn empty answer looks like a quiet market. Why a stopped feed has to arrive as an error, and what the SI does with it.
- SI and the Retail Trader: The Read That Used to Need a DeskThe data is public. Reading all of it was the part that needed a desk. What a markets SI closes for a retail trader, and what it leaves open.
- Names Repeat: How a Markets SI Keeps Markets ApartOne ticker, several markets. Why perp books are never added together, why tokens are keyed on contracts, and what to listen for in an answer.
- Why the Read and the Trade Stay SeparateA reader with a position stops being neutral. Why Dr. NoVo reads and never trades, and where the acting can happen if you want it.
- How to Check What a Markets SI Told YouFind the number on the dashboard, check its age, check its venue, then ask where it came from. A one-minute routine.
- What a Markets SI Cannot Know About YouYour account, your size, your horizon, your tolerance for loss. None of it is in a feed, and all of it decides the trade.
- The Next Few Years: More Markets That Never Close, and More to ReadRound-the-clock markets on stocks already exist. What more of them would mean for the reading load, and what a trader should ask of an SI.
- Asking a Markets SI Where SPY Sits Against the Gamma FlipSide, distance, meaning and age. The parts of a good answer about SPY and its gamma flip, and what should never be in one.
- Asking Where the Walls Are, and What the SI Will Not Say About ThemWhere each wall sits, how far away, and how old the read is. Then the list of things a markets SI should refuse to say about a wall.
- Asking About the Expected Move With Hours Left in the DayHow much of the day’s expected range is already used, what it is measured from, and why the answer is never a cap on the afternoon.
- Asking a Markets SI What Changed Since YesterdayA change needs two readings. What a markets SI can set against yesterday, and why it has to name the span its record covers.
- Asking an SI to Explain a Term in the Middle of a SessionOne line of definition, one line tying it to the reading on screen, one line on what the term does not mean. How to ask without losing the session.
- The Follow-Up Question That NarrowsFour ways to narrow a follow-up: instrument, venue, time, comparison. And the moment the next question stops being a reading.
- When a Markets SI Says the Data Is DelayedThree kinds of delay, how to tell which one you have, and why hearing about it is a good sign.
- Dr. NoVo’s Written Reads Versus a Question You Ask YourselfWhat the written reads are for, what a question of your own is for, and why the read comes first.
- Using a Markets SI to Check Your Own Reading of the MapRead the map, ask the SI to describe it cold, and compare. The four usual reasons two readings differ, and what the check cannot do.
- Asking a Markets SI About a Stock Token’s FlowSupply now, flow over a day and a week, and the span the record covers. Plus the inference a markets SI should decline to make.
- Asking a Markets SI the Same Question an Hour ApartWhy two answers to one question differ, how to compare them by their ages, and the one case where a repeat answer should worry you.
- Asking for a Stock Token’s Price on a SundayA weekend quote can be too wide to mean much. The four numbers a markets SI can offer in its place, each with its label.
- After the Bell: What to Ask a Markets SI Once the Cash Market ShutsWhich readings rest at the close, which keep trading, and four questions for the first hour after the bell.
- Asking a Markets SI to Compare SPY, QQQ and IWMWhat a side-by-side read of three dealer maps contains, why distances are given in percent, and where IWM always needs a note.
How It Works 1
- What Is Algorithmic Trading?Algorithmic trading means software executes trades by predefined rules instead of a human clicking.