MARKET FLOW RESEARCH
Independent research on crypto market microstructure. We study second-by-second order-book and order-flow data across major coins.
Corrections, not exitsA Detector for Corrections Inside a Move — and Why It Took a New Way of Measuring
We stopped measuring how loud the order book is and started measuring how much wall stands per unit of aggression — eight features collapsed into four ratios. On that new scale a class appears that we could not see before: corrections inside a move, 5,396 of them, events that already look like a reversal without being one. Three detectors find them at 0.94 precision on a held-out half, and an external 0.8% zigzag confirms the class survives after loudness is matched away (×1.69). For a bot, that is the difference between holding a trend and being shaken out of it.
Line 61 liveBot 6, Line 61: Nine Trades, Eight Winners, and Why We Are Not Celebrating
Line 61 of Bot 6 holds one position at a time and has been live since 17 July 2026: 31 days, 9 closed trades, +11.81 USD on a 100 USD slot, win rate 89%. Its entry gate is agreement between two independent models plus a context check; its exits are a 2% target, a 4% stop and a hard 72-hour clock. This is the complete record, including the comparison with its twin line running the identical recipe — which is the part that keeps us honest.
Line 60 liveBot 6, Line 60: A Bot That Mostly Waits — and What the Clock Costs It
Line 60 of Bot 6 holds one position at a time and has been live since 15 July 2026: 33 days, 9 closed trades, +0.68 USD on a 100 USD slot, win rate 44%. Its entry gate is agreement between two independent models plus a context check; its exits are a 2% target, a 4% stop and a hard 72-hour clock. This is the complete record, including the comparison with its twin line running the identical recipe — which is the part that keeps us honest.
Bot 4 liveBot 4: What Forty Days of Live Paper Trading Actually Look Like
Bot 4 has been trading live on paper since 09 July 2026 — 40 days, 49 closed trades, +29.53 USD on 600 USD of capital, a 80% win rate, against +1.49% on average for buying and holding the same coins. This is the full record: the rules it never deviates from, every closed trade, the open positions right now, and the hourly referee that can hand the account to a freshly trained challenger — which has happened 4 times so far.
GatesGates: The Part of a Trading Bot That Decides Not to Trade
A trading bot's model produces a number; its gate decides whether that number is worth a fee. This article measures what gates actually cost. Demanding a signal persist two bars instead of one raises precision from 0.209 to 0.238 and throws away 25% of the opportunities. Bot 4 stacks four gates and still lands inside the noise across random seeds. Bot 6 gates on agreement between two models — and two live lines running that identical gate for a month finished +11.81 and +0.68 USD apart. Gates buy precision with coverage; nothing here is free.
How far, not which wayThe Order Book Tells You How Far, Never Which Way
We asked eight order-book features the same two questions at 16 horizons from one second to a day, on six coins: how far will the price move, and which way. Size answers — ρ 0.30 at a second, still 0.11 at an hour. Direction never does: -0.002 at a minute, -0.003 at a day. Then we bet real rules on both answers over 30 out-of-sample days: the volatility bet makes +4.97 bps a trade, the direction bet loses 5.95. This is the measurement that decides what our bots are allowed to bet on.
Typhoon+Typhoon+: A Signal That Finds the Perfect Trader's Zones — and Still Loses Money
We drew the zones a perfect trader would use — 0.9% zigzag turns, a 0.15% band around each one — and found that the price sits inside them barely 3% of the time. A single gradient-boosting model, pooled over six coins, then finds 74% of those zones on days it never saw. It also fires false 86% of the time, leans mostly on price geometry rather than the order book, and loses 122% when traded plainly against 93% for buy & hold. This is the article about a signal that finds the right places and still cannot pay the fee.
Moves, not noiseWe Taught a Network to See a Move. It Only Heard How Loud It Was.
We trained three networks on the same 56,263 order-book windows and learned two things we did not want to learn. A single number — how loud the window is — matches a convolutional network on all 1,680 of them (0.7575 against 0.7571). And once you match windows by that number, the inflow features that carried the whole model separate nothing at all. What does survive is small, directional, and points at a different kind of bot than the one we set out to build.
Dataset cleaning recipeA Recipe, Not a Result: How We Clean an Order-Book Dataset
This is the least glamorous and most useful study of the series: not a finding, but a procedure. How to take a raw dataset of order-book windows and produce a clean one — 56,263 windows in, 31,212 out, 95% of the reversals still there — with every step checked, every trap written down, and the whole thing runnable on another coin by one command.
The cleaned datasetThrowing Away a Third of the Data and Keeping 98% of the Reversals
If a third of your data provably contains almost nothing you are looking for, it should not be in the training set. We removed 18,744 of 56,263 windows — everything two independent definitions of 'quiet' agree on — and kept 98.1% of all the reversal windows.
Week by weekTwenty-Five Weeks, Twenty-Five Rebuilds: Which Clustering Survives
A clustering that only exists once is a story, not a result. So we rebuilt it 25 times — every week of the dataset from scratch, its own PCA, its own UMAP, its own clusters — and compared each week with the answer found on the whole dataset. One of the two methods reproduces. The other does not, and it is the fashionable one.
The falling halfTops Hide, Bottoms Don't: an Asymmetry We Did Not Expect
This is the mirror of the previous study: the fall from a top to a bottom, 27,180 windows, the same pipeline to the letter. The structure repeats — and one number does not. Tops hide from the order book four times more often than bottoms do.
The rising halfThe Rising Half of a Move: What the Order Book Looks Like Between a Bottom and a Top
Half of every price move is a climb from a bottom to a top. We took only that half — 26,921 windows of the order book — and clustered it blind. The structure that comes out is the same one the whole dataset gives, which is good news: it means the classes are not an artefact of mixing rises and falls together.
Classes without a teacherOne Axis, Again: Clustering 56,000 Order-Book Windows Without a Teacher
Take 56,263 windows of the order book, 210 seconds each, eight features per second. Tell the algorithm nothing — not the price, not the time, not our own signals. Ask only one thing: does this pile of windows fall apart into groups by itself? It does, along exactly one axis, and that axis is not the one anybody hopes for.
Pooled reversal modelOne Network for Three Market States: What a Pooled Reversal Model Learns
We trained one network on the events of three different market states at once — 55,929 events, 3,758 of which sit on a real turning point — and asked it a single question: is this event a reversal or an ordinary event of its own class? The answer is interesting in a way we did not plan: the model works, the validation set lies about which model is best, and an unsupervised split of the same pool finds classes that have nothing to do with reversals at all.
Separating the signalThree Classes, One Question: What It Takes to Separate a Reversal
Three market states, one question: can an order-book event that sits on a turning point be told apart from the ordinary events of its own class? This is the overview of that work — the three per-class studies side by side, every engine we tried in between, and the parts that hurt: a grid search that bought 0.02 AUC, a network on 1,680 numbers that lost to a single average, and a threshold that looked like 63% precision until it was asked to survive two months of new data, where it became 39%.
Class 2 reversalsClass 2: the Middle State Where No Single Feature Wins
The **class 2** state fires on 21,704 windows of this dataset, and 1,961 of them (9.0%) sit on a turning point of price. This page asks one question and answers it with one frozen network: can a reversal be told apart from the ordinary events of its own class, and which of the eight order-book features carries that difference? Best single feature: `vol_buy` at 15.8% precision. Best set: 6 features at 23.5% precision and 23.6% recall, against a base rate of 9.0% — ×2.6.
Calm reversalsReversals in a Quiet Market: Where 2.5% of Events Hide
The **calm** state fires on 29,303 windows of this dataset, and 739 of them (2.5%) sit on a turning point of price. This page asks one question and answers it with one frozen network: can a reversal be told apart from the ordinary events of its own class, and which of the eight order-book features carries that difference? Best single feature: `vol_buy` at 10.8% precision. Best set: 8 features at 14.9% precision and 15.3% recall, against a base rate of 2.5% — ×6.0.
Storm reversalsThe Storm Class: Which Order-Book Feature Marks a Reversal
The **storm** state fires on 5,249 windows of this dataset, and 1,085 of them (20.7%) sit on a turning point of price. This page asks one question and answers it with one frozen network: can a reversal be told apart from the ordinary events of its own class, and which of the eight order-book features carries that difference? Best single feature: `vol_buy` at 49.5% precision. Best set: 5 features at 54.1% precision and 50.0% recall, against a base rate of 20.7% — ×2.6.
Reversal DNAWe Went Looking for the DNA of a Reversal. We Found a Ceiling Instead.
An earlier study on this dataset (175 days of BTC) found 271 order-book events that sit exactly on the turning points of price, and showed that a model cannot separate them from the thousands of ordinary events of their own class. This study asks a narrower question: forget separating a reversal from its class — is there anything, on its own, that a reversal event's 271 examples share? Nine different methods attack the question from nine angles: a two-condition threshold rule, a raw-vector kinship check, a full neural detector, a scan for the shortest useful slice of the window, four models on four quarters of it, one model on all of its 30-second slices at once, and three independent models — one per parent market state. Every method finds something real, reproducible, and well above every null control we built. None of them clears the bar a trading signal needs. The best operating point we found, buried inside the loudest of four market states, is right roughly one time in three.
SignalsWe Found the Reversal Signal. Machine Learning Could Not Tell It Apart.
A market moves in legs: a few percent one way, a turning point, then a few percent the other. This study asks whether the order book carries an event that marks the turn — and whether that event can be separated from the thousands of ordinary events of the same class. On 175 days of BTC the first half works: groups of signals pile up at turning points 3.7× more often than chance, every class shows the same reversal signature, and inside a storm the shape of the flows tells a top from a bottom where price itself says nothing. The second half does not. Every way we tried to learn 'is this a reversal' landed on top of its own null control, and a class retrained with all reversal windows removed still fires on them — harder than on its ordinary events. The signal is real; the discriminator is not.
NetsSixteen Networks, One Working Answer — and the Price Benchmark That Nearly Killed It
We trained sixteen one-class autoencoders on Bitcoin order-book windows: four market states, and inside each state one network per phase of the price move. Each network saw only its own kind of window and nothing else — no negative examples at all. One thing out of sixteen works: inside a storm you can tell a bottom reversal from a top one. On half the data that looked like AUC 0.6264; measured properly on all 800 events it is 0.5928. Then a one-line price benchmark scored 0.8548 on the same question. This article is about what survives that, and where it survives.
StatesDoes the Phase of a Move Change What the Order Book Looks Like?
We have four detectors of market state and a map of where price is in its move — reversal zones and the legs between them. Laying one over the other answers a question that sounds simple and is not: does the phase of a move change what a market state looks like? On 171 days of BTC the answer splits. The count of events barely moves — each class fires roughly in proportion to how long the phase lasts. What moves is their strength, and only for the quiet classes. And in one narrow place the order book finally beats price: telling a top from a bottom inside a storm.
AutoencoderEight Ways to Compress 210 Seconds: the Autoencoder That Lost to PCA
We cut 170 days of per-second Bitcoin order-book data into 50,143 back-to-back windows and pushed them through eight different compressions — PCA, a convolutional autoencoder, and six variants of both — to see whether a network finds market structure a linear method misses. It does not. Its raw stability is the best in the table and most of that stability survives when the data is shuffled into noise, which means it was never structure at all.
Market statesTwo Poles of Market Activity, Found Without a Teacher on Six Coins
We cut 122–141 days of per-second order-book data on 6 coins into 164,342 windows of 210 seconds, showed a clustering pipeline nothing but the eight order-book features, and asked whether the market falls into natural states. It does — two poles of flow activity with a wide grey zone between them — and the same pipeline run on shuffled data produces nothing, which is what makes the answer worth reporting. The walls turn out to be irrelevant to the split, and the autoencoder we brought in to beat PCA lost to it.
ReplicationFour Market States, Found Twice by Two Independent Pipelines
Four market states, found twice by two pipelines that share no code. We wrote our research recipe down as an executable diary, then wrote a second implementation from that text alone — different seed, different block split, different network initialisation — and ran it over the same 54,764 windows of BTC order-book data. The states came back: 93.0% of windows landed in the same one (ARI 0.7726), and two independently trained detectors fire on the same 98.5% of windows. Where both fire, the next hour's price range is ×1.432 the median of the same day.
PivotsLocal tops and bottoms in the order book: what four trained models actually see
We marked every local top and bottom on 171 days of per-second Bitcoin order-book data — 734 of them, defined by a rule rather than by hand — and asked four trained market-state detectors whether they can see them. The zone itself is invisible. The moment of the extremum is not, and neither is 'an extremum within the next hour'. But a plain price range from the same window beats the order book at both, and the honest edge turns out to live somewhere else entirely: in telling a top from a bottom when price itself has nothing to say.
Window classesThere Are No Classes in the Order Book — Only One State That Survives
We locked a 210-second window to its own 1,680 numbers — eight order-book features, no norm, no price, no clock — and asked whether the market falls into classes. It does not: the gap statistic sits at 0.0017, silhouette matches noise, and at some K the shuffled null is more stable than the data. One state survives every check: 9.8% of windows where flows run hot and both walls thin out, followed by ×1.78 the usual hourly range.
Event classesEvent Classes Found Without a Teacher: 3 Survive, 60% Are Noise
We asked the order book to sort its own events into classes — 2,786 events, eight features, no price and no human labels. Out of 512 configurations only 5 produced anything stable, 60% of events belong to no class at all, and the three that do exist raise volatility while leaving direction at a coin flip.
SignalsThe Alphabet of the Order Book: 6,561 Possible States, 333 Real Ones
We described the order book as a single word: eight features, three states each. Of the 6,561 words that could exist, only 333 ever occur — and when we tested that alphabet out of sample, it described the market well and predicted it poorly.
Signal standard · BTCFrom Calm to Calm: a Standard for What Counts as a Signal (BTC)
We stopped defining market signals with a stopwatch. A signal is a continuous departure from calm, bounded by calm on both sides — the market decides where it starts and ends. Here is the standard, applied second by second to 167 days of BTC, with every event classified and located on the price path.
Side vs sideSide Against Side: Resistance and Support Compared
We put all six order-book features grouped into the resistance side and the support side into one study and asked how the pieces relate, which one leads, and what the combination predicts. Same boundary as always: it speaks about size, not side.
Flow vs wallFlow Against the Wall: When Volume Meets Resting Liquidity
We put executed volume hitting the resting wall on the opposite side into one study and asked how the pieces relate, which one leads, and what the combination predicts. Same boundary as always: it speaks about size, not side.
Wall lifecycleThe Life of a Sell Wall: Standing, Growing, Thinning
We put the three phases of the same sell-side wall — how much stands there, what arrives, what leaves into one study and asked how the pieces relate, which one leads, and what the combination predicts. Same boundary as always: it speaks about size, not side.
Sell volumeExecuted Sell Volume, Measured Alone
We isolated executed sell volume — one feature, no partner, no composite — and measured what it predicts second by second across six coins. The answer is the size of the next move, never its side.
Buy volumeExecuted Buy Volume, Measured Alone
We isolated executed buy volume — one feature, no partner, no composite — and measured what it predicts second by second across six coins. The answer is the size of the next move, never its side.
Buy drainDrain Out of the Buy Wall: Liquidity Leaving Before the Move
We isolated drain out of the buy wall — one feature, no partner, no composite — and measured what it predicts second by second across six coins. The answer is the size of the next move, never its side.
Buy build-upBuild-Up Into the Buy Wall: What Arriving Liquidity Predicts
We isolated build-up into the buy wall — one feature, no partner, no composite — and measured what it predicts second by second across six coins. The answer is the size of the next move, never its side.
Sell drainDrain Out of the Sell Wall: Liquidity Leaving Before the Move
We isolated drain out of the sell wall — one feature, no partner, no composite — and measured what it predicts second by second across six coins. The answer is the size of the next move, never its side.
Sell build-upBuild-Up Into the Sell Wall: What Arriving Liquidity Predicts
We isolated build-up into the sell wall — one feature, no partner, no composite — and measured what it predicts second by second across six coins. The answer is the size of the next move, never its side.
Buy wallThe Resting Buy Wall, Measured Alone
We isolated the resting buy wall — one feature, no partner, no composite — and measured what it predicts second by second across six coins. The answer is the size of the next move, never its side.
Sell wallThe Resting Sell Wall, Measured Alone
We isolated the resting sell wall — one feature, no partner, no composite — and measured what it predicts second by second across six coins. The answer is the size of the next move, never its side.
Support cycleThe Support Cycle: Liquidity Arriving vs Leaving
We measured the same buy-side wall growing and thinning second by second across six coins, and asked the only question that matters: does it tell you anything about what happens next? It does — about size, not direction.
Resistance cycleThe Resistance Cycle: Liquidity Arriving vs Leaving
We measured the same sell-side wall growing and thinning second by second across six coins, and asked the only question that matters: does it tell you anything about what happens next? It does — about size, not direction.
InflowLiquidity Arriving: What a Growing Wall Says Next
We measured fresh resting liquidity arriving into the book second by second across six coins, and asked the only question that matters: does it tell you anything about what happens next? It does — about size, not direction.
DrainLiquidity Pulled: What Happens When a Wall Drains
We measured resting liquidity being pulled away from the book second by second across six coins, and asked the only question that matters: does it tell you anything about what happens next? It does — about size, not direction.
WallsThe Wall That Goes Quiet: What Resting Liquidity Predicts
We measured resting limit liquidity sitting on both sides of the book second by second across six coins, and asked the only question that matters: does it tell you anything about what happens next? It does — about size, not direction.
AboutAbout Market Research Lab — What We Collect and Why
Most market commentary is storytelling. We built something testable instead: 166 days of second-by-second order-book data across six coins, and a rule that nothing gets published unless it survives out-of-sample.
VolumeVolume Is the Fuel — Not the Steering Wheel
Everyone asks whether volume pushes price up or down. We measured it second-by-second on six coins. The honest answer surprises people.
Order flow predicts how much, not which way
Across six coins, flow surges line up with bigger moves — but not their direction. What that means for anyone trading the tape.