Intraday momentum strategy

On ES futures, the intraday momentum strategy lost $99,524 after costs and ran a $100,000 account down to its margin on May 2, 2025. The run stops there.

TrendIntraday1-minute barsBacktested Nov 6, 2026

Intraday momentum backtest, the result

Contract

E-mini S&P 500

  • −$99.5K

    Net after costs

    After $64,762 in fees and slippage

  • 1 of 10

    Years that made money

    January 2016 to May 2025

  • −$100K

    Largest drawdown

    Peak to trough, 1 contract

  • −$44

    Average trade

    2,271 trades

Intraday momentum on ES, net after costs by month, from January 2016 to May 2025: −$99,524; buying and holding one ES contract: +$236,212

Net after costs by month, January 2016 to May 2025.

Intraday momentum rules

The first half hour's move sets the side of one trade in the last half hour of the day.

A drawing of the rules on a made-up day, not a result.

  1. The first half hour's return runs from the prior day session's last price before 16:00 to the 10:00 New York price.
  2. At 15:30 the strategy goes long if that return was positive and short if it was negative.
  3. The position is closed at 16:00 New York.
Decides on
1-minute bars
Holds
Nothing overnight
Parameters
open minute 570, signal minute 600, entry minute 930, close minute 960

Results by year

It made money in 1 of 10 years on ES. Its best year was 2023, +$206, and its worst 2021, −$23,498. The account was closed out on May 2, 2025, so the years stop there.

Net after costs by year on ES, with trades, win rate, largest drawdown and buying and holding the same contract
YearNetTradesWin rateDrawdownBuy and hold
2016−$9,84124336%−$10,582+$11,497
2017−$10,35723936%−$10,926+$21,936
2018−$9,76824145%−$17,709−$8,589
2019−$8,59824246%−$9,495+$35,436
2020−$3,85624644%−$20,682+$27,761
2021−$23,49824641%−$26,551+$51,361
2022−$22,87724545%−$24,466−$45,939
2023+$20624346%−$12,513+$38,435
2024−$5,83524448%−$8,599+$42,947
2025, Jan to May−$5,0998244%−$12,952+$37,010

Intraday momentum backtest results

On ES it lost $34,763 before costs, then paid $64,762 in fees and slippage.

Net = before costs − fees − slippage
ES: −$34,763 − $7,987 − $56,775 = −$99,524
Every figure of the Intraday momentum backtest, by contract
FigureESNQ
Net after costs−$99,524−$99,095
Before costs−$34,762−$45,765
Fees$7,987$7,970
Slippage$56,775$45,360
Trades2,2712,268
Trades a year239239
Win rate43%47%
Profit factor0.770.83
Average trade−$44−$44
Average trade, 95% interval−$66 to −$21−$76 to −$12
Sharpe ratio-1.24-0.89
Largest drawdown−$100,264−$112,663
Time in the market1%1%
Buying and holding the contract+$236,212+$401,004

The whole interval is under zero: after costs, the average trade lost money.

Intraday momentum code and Pine Script

The strategy as the backtest ran it, and the Pine Script our compiler wrote from it for TradingView.

Intraday momentum
intraday_momentum.py
1from atlantive import BUY, NEW_YORK, SELL, Bars, Session, Strategy2 3 4class IntradayMomentum(Strategy):5    """Market intraday momentum (Gao, Han, Li and Zhou, 2018), New York day session, one-minute bars.6 7    The first half hour's return runs from the prior day session's last price before 16:00 to the8    10:00 price. Its sign sets the side of a trade opened at 15:30 and closed at 16:00 the same9    day: long after a rise, short after a fall, nothing when it is flat.10    """11 12    data = "bars"13 14    class Params:15        open_minute: int = 57016        signal_minute: int = 60017        entry_minute: int = 93018        close_minute: int = 96019        clip: int = 120 21    class State:22        clock: Session(zone=NEW_YORK)23        bars: Bars(interval_ns=60_000_000_000)24        prior_close: float25        prior_day: int26        day_close: float27        day_close_day: int28        early_close: float29        early_day: int30        entered_day: int31 32    def on_event(self, view, ev, orders):33        self.clock.update(ev)34        if not self.bars.update(ev):35            return36        minute = self.clock.prev_minute37        day = self.clock.prev_day38        close = float(self.bars.prev_close)39        ends = minute + 140        if view.position != 0:41            if ends >= self.p.close_minute or day != self.entered_day:42                if view.position > 0:43                    orders.ioc(side=SELL, qty=self.p.clip)44                else:45                    orders.ioc(side=BUY, qty=self.p.clip)46        if minute >= self.p.open_minute and minute < self.p.close_minute:47            if self.day_close_day != day:48                if self.day_close_day != 0:49                    self.prior_close = self.day_close50                    self.prior_day = self.day_close_day51                self.day_close_day = day52            self.day_close = close53            if ends <= self.p.signal_minute:54                self.early_close = close55                self.early_day = day56            if ends >= self.p.entry_minute and ends < self.p.close_minute and self.entered_day != day:57                if view.position == 0 and self.prior_day != 0 and self.early_day == day:58                    move = self.early_close - self.prior_close59                    if move > 0:60                        orders.ioc(side=BUY, qty=self.p.clip)61                        self.entered_day = day62                    elif move < 0:63                        orders.ioc(side=SELL, qty=self.p.clip)64                        self.entered_day = day
1//@version=62// IntradayMomentum, exported from Atlantive.3// Chart simulation: decisions use completed bars; market orders fill at the next bar open.4// Native fills, fees, data gaps and session boundaries can differ. Re-test on the target symbol.5// Use standard time-based candles and the strategy's timeframe, not synthetic chart prices.6// Pine v6 trims old trade records at its order limit; the strategy keeps calculating.7// Margin is explicitly disabled to retain the native signal simulation's sizing.8strategy("IntradayMomentum", overlay=true, initial_capital=100000.0, commission_type=strategy.commission.cash_per_contract, commission_value=1.68, default_qty_type=strategy.fixed, default_qty_value=1, calc_on_every_tick=false, process_orders_on_close=false, slippage=0, margin_long=0, margin_short=0)9 10if timeframe.in_seconds() != 6011    runtime.error("IntradayMomentum was exported for the 1 minute timeframe; set the chart to 1.")12 13open_minute = input.int(570, "open_minute", minval=-9007199254740991, maxval=9007199254740991)14signal_minute = input.int(600, "signal_minute", minval=-9007199254740991, maxval=9007199254740991)15entry_minute = input.int(930, "entry_minute", minval=-9007199254740991, maxval=9007199254740991)16close_minute = input.int(960, "close_minute", minval=-9007199254740991, maxval=9007199254740991)17clip = input.int(1, "clip", minval=-9007199254740991, maxval=9007199254740991)18 19_q_safe_int(x) =>20    if math.abs(x) > 900719925474099121        runtime.error("an integer left the exact chart range; this run cannot be compared faithfully")22    int(x)23_q_int(x) => _q_safe_int(x < 0 ? math.ceil(x) : math.floor(x))24_q_iadd(a, b) => _q_safe_int(a + b)25 26_q_close = _q_int(math.round(close * 1000000000.0))27 28var float prior_close = 0.029var int prior_day = 030var float day_close = 0.031var int day_close_day = 032var float early_close = 0.033var int early_day = 034var int entered_day = 035// clock: completed chart bar's opening timestamp (America/New_York).36_q_clock_prev_minute = hour(time, "America/New_York") * 60 + minute(time, "America/New_York")37_q_clock_prev_second = _q_clock_prev_minute * 60 + second(time, "America/New_York")38_q_clock_prev_weekday = (dayofweek(time, "America/New_York") + 5) % 739_q_clock_prev_day = int(timestamp("UTC", year(time, "America/New_York"), month(time, "America/New_York"), dayofmonth(time, "America/New_York"), 0, 0) / 86400000)40// Current clock: this chart bar's scheduled close, known without a future bar.41// A native next event after a data gap can carry a later time.42_q_clock_minute = hour(time_close, "America/New_York") * 60 + minute(time_close, "America/New_York")43_q_clock_second = _q_clock_minute * 60 + second(time_close, "America/New_York")44_q_clock_weekday = (dayofweek(time_close, "America/New_York") + 5) % 745_q_clock_day = int(timestamp("UTC", year(time_close, "America/New_York"), month(time_close, "America/New_York"), dayofmonth(time_close, "America/New_York"), 0, 0) / 86400000)46_q_clock_seen = 147int minute_l = na48int day = na49float close_l = na50int ends = na51float move = na52 53minute_l := _q_int(_q_clock_prev_minute)54day := _q_int(_q_clock_prev_day)55close_l := _q_close * 1.056ends := _q_int(_q_iadd(minute_l, 1))57if _q_int(strategy.position_size) != 058    if ends >= close_minute or day != entered_day59        if _q_int(strategy.position_size) > 060            _q_qty1 = _q_int(clip)61            if _q_qty1 <= 062                runtime.error("market order quantity must be a positive whole unit")63            _q_pos1 = _q_int(strategy.position_size)64            if _q_pos1 < 0 or _q_pos1 > 0 and _q_qty1 < _q_pos165                runtime.error("this order would add to or partially reduce a position, so its trade ledger would not be faithful")66            strategy.order("q1", strategy.short, _q_qty1)67        else68            _q_qty2 = _q_int(clip)69            if _q_qty2 <= 070                runtime.error("market order quantity must be a positive whole unit")71            _q_pos2 = _q_int(strategy.position_size)72            if _q_pos2 > 0 or _q_pos2 < 0 and _q_qty2 < -_q_pos273                runtime.error("this order would add to or partially reduce a position, so its trade ledger would not be faithful")74            strategy.order("q2", strategy.long, _q_qty2)75if minute_l >= open_minute and minute_l < close_minute76    if day_close_day != day77        if day_close_day != 078            prior_close := day_close79            prior_day := _q_int(day_close_day)80        day_close_day := _q_int(day)81    day_close := close_l82    if ends <= signal_minute83        early_close := close_l84        early_day := _q_int(day)85    if ends >= entry_minute and ends < close_minute and entered_day != day86        if _q_int(strategy.position_size) == 0 and prior_day != 0 and early_day == day87            move := early_close - prior_close88            if move > 089                _q_qty3 = _q_int(clip)90                if _q_qty3 <= 091                    runtime.error("market order quantity must be a positive whole unit")92                _q_pos3 = _q_int(strategy.position_size)93                if _q_pos3 > 0 or _q_pos3 < 0 and _q_qty3 < -_q_pos394                    runtime.error("this order would add to or partially reduce a position, so its trade ledger would not be faithful")95                strategy.order("q3", strategy.long, _q_qty3)96                entered_day := _q_int(day)97            else if move < 098                _q_qty4 = _q_int(clip)99                if _q_qty4 <= 0100                    runtime.error("market order quantity must be a positive whole unit")101                _q_pos4 = _q_int(strategy.position_size)102                if _q_pos4 < 0 or _q_pos4 > 0 and _q_qty4 < _q_pos4103                    runtime.error("this order would add to or partially reduce a position, so its trade ledger would not be faithful")104                strategy.order("q4", strategy.short, _q_qty4)105                entered_day := _q_int(day)

How it was tested

The published rules, never tuned on the data, with real costs on every fill. Every strategy here is tested the same way.

Market data
CME Globex 1-minute bars, Jan 2, 2016 to Jul 31, 2026
Rules
As published, with the published parameters, never tuned on this data
Size
1 contract on every trade
Contract
The most traded one, rolled as the market moved
Fees
The broker's $0.50 a side, plus CME's and the NFA's fees when the window opens
Slippage
1 tick a side on ES, 2 in NQ's regular session and 3 outside it, 1 on other markets, where it was not measured
Stops and entries
Tested on 1-second closes and filled at the next bar
Contracts traded
ES: 43 contracts, ESH6 to ESU6NQ: 43 contracts, NQH6 to NQU6
Costs paid
ES: $7,987 in fees, $56,775 in slippageNQ: $7,970 in fees, $45,360 in slippage
Warm-up
None: each contract reads only its own bars
Flagged days
ES: NoneNQ: None Days the data holds too few bars for. Flagged, not removed.

Could you pass
a prop firm challenge
with the intraday momentum strategy?

A backtest says whether a strategy makes money. Our AI runs its trades through the rules of every prop firm account, then tells you which one it would pass and at what size.

No card needed. Free credits every month.

  • Most money: Blue Guardian Futures Direct 50K, $5,084
  • Best payout odds: Funded Futures Family Straight to Funded 50K, 98%
  • Fastest pass: Phidias Express to Live 50K, 11 days
Blue Guardian Futures Direct 50K
Most money

$5,084

Median net across 2,000 simulated runs

Evaluation
None
First payout
97%
Fees paid
$1,521

Median net across 2,000 simulated runs

Best 5%$13,143Worst 5%−$412
Day 060120180
Example: ES opening range breakout

Questions about the intraday momentum strategy

What is the intraday momentum strategy?

The first half hour's move sets the side of one trade in the last half hour of the day. The rules follow Lei Gao, Yufeng Han, Sophia Zhengzi Li, Guofu Zhou, Market Intraday Momentum, Journal of Financial Economics 129(2), 394-414 (2018). Atlantive backtested it on CME futures from January 2016 to July 2026 after costs.

Is the intraday momentum strategy profitable on ES futures?

Not in this backtest: on ES futures from January 2016 to May 2025 it lost $99,524 after costs, over 2,271 trades, positive in 1 of 10 years; on NQ it lost $99,095. Buying and holding one ES contract over the same window made $236,212. The average trade was −$44, its 95% interval −$66 to −$21. These are hypothetical results of a backtest, not of trading.

What are the intraday momentum strategy's rules?

The first half hour's return runs from the prior day session's last price before 16:00 to the 10:00 New York price. At 15:30 the strategy goes long if that return was positive and short if it was negative. The position is closed at 16:00 New York. The rules follow Lei Gao, Yufeng Han, Sophia Zhengzi Li, Guofu Zhou, Market Intraday Momentum, Journal of Financial Economics 129(2), 394-414 (2018). Its parameters are the published ones, never tuned on the data it was tested on.

How was the intraday momentum strategy backtested?

On CME Globex data from January 2016 to July 2026, one contract, on 1-minute bars, rolled to the most traded contract as the market moved, with the broker's and CME's fees and the slippage measured on each market. Stops and entries were tested on 1-second closes and filled at the next bar. Nothing was fitted to the data.

Can I run the intraday momentum strategy in TradingView?

Yes. The page carries its Pine Script, written by Atlantive's compiler from the same code the backtest ran, for TradingView's strategy tester. A chart's fills and fees can differ from the backtest's, so test it again on the symbol you trade.

Can I change the intraday momentum strategy and test it again?

Yes. Rerun it in Atlantive: a new chat opens with the strategy's rules in the box, for you to read, change and send. The agent writes the code, backtests it on the market and window you name, and reports the result with its costs.

Rerun it in Atlantive. Change the market, the dates or a rule, then send it.

A new chat opens with this in the box

Backtest the Gao, Han, Li and Zhou intraday momentum rule on ES, 2016-01-02 to 2026-07-31, one contract on a $100,000 account with default costs: the return from the prior day session's 16:00 close to 10:00 New York sets the side; enter at 15:30, exit at 16:00.

Never sent for you

May we measure this visit?

With your consent, Google Analytics and PostHog count visits to these pages. You can separately allow Google Ads to measure visits from our ads. Visit measurement starts only after you choose. Cookie policy