Backtest Lab
A backtest cannot prove an idea works. It can show quickly that an idea does not. Judge a rule set
by how little it degrades when Indian charges, overnight gaps, unseen years and bad luck are piled
on, and treat a spectacular first run as a reason for suspicion.
Commands
python3 scripts/backtest.py strategies # rules and defaults
python3 scripts/backtest.py run --csv tcs.csv --strategy sma-cross --params fast=20 slow=50
python3 scripts/backtest.py run --symbol POLYCAB --strategy 52w-high --risk-pct 1 --tax --trades-csv t.csv
python3 scripts/backtest.py run --csv hdfcbank.csv --strategy donchian-breakout --regime-csv nifty.csv
python3 scripts/backtest.py run --csv nifty.csv --strategy sma-cross --segment futures --lot-size 65 \
--allow-short --leverage 3 --size-pct 300
python3 scripts/backtest.py sweep --csv tcs.csv --strategy sma-cross --grid fast=10,20,30 slow=50,100,200
python3 scripts/backtest.py walkforward --csv tcs.csv --strategy donchian-breakout \
--grid entry_n=20,40,55 exit_n=10,20 --is-bars 756 --oos-bars 252
python3 scripts/backtest.py montecarlo --csv tcs.csv --strategy ema-pullback --sims 2000 --seed 7
python3 scripts/backtest.py montecarlo --from-trades t.csv --ruin-dd 25
Inputs follow technical-analysis: --csv, --candles (broker-MCP JSON, null candles skipped) or
--symbol (yfinance, --period 10y). --start sets the first trading day while earlier bars still
warm up the indicators. --grid also takes ranges (fast=10:50:10). Every command takes --json.
Bad input exits 2 with one error: line.
Strategies (--strategy, override with --params key=value)
| Name |
Rule (long side; shorts mirror it) |
Defaults |
| sma-cross |
fast SMA crosses above slow; out when back below |
fast 20, slow 50, stop 3×ATR |
| ema-pullback |
close above a rising trend EMA, low tags the EMA, close back above it |
ema 20, trend 100, 2×ATR, target 2R, 20 bars |
| rsi-reversion |
RSI(period) below buy_below while above the trend SMA; out above sell_above |
2, 10, 70, trend 200, 10 bars |
| donchian-breakout |
close above the prior entry_n high; out below the prior exit_n low |
20 / 10, 2×ATR |
| bollinger-reversion |
close below the lower band; out at the middle band |
20, k 2, trend 0 (off), 20 bars |
| 52w-high |
close above the prior lookback-bar high; out below the exit SMA |
252, exit_ma 50, 2.5×ATR |
Every strategy also takes stop_atr (k × ATR14 from the fill), stop_pct (overrides it),
target_r and max_hold (bars), where 0 turns each one off. There is no custom-code hook: new
rules are added to the script as reviewed code.
How orders and costs are simulated
- No look-ahead. Signals use bars up to and including the signal bar's close. The order fills at
the next bar's open, never at the close that produced it.
- Stops and targets rest in the market. A gap through the level fills at the open (a stop at ₹101
after a ₹96 open books ₹96). If one bar touches both, the stop is assumed to have filled first.
- Slippage
--slippage-bps (default 5) on every fill. Use 15–30 for small caps.
- Charges come from
trading-costs (charges.py) for each round trip, by --segment delivery|intraday|futures and --broker. A delivery buy sold the same day is charged as intraday.
- Sizing:
--size-pct (default 100% of equity), --risk-pct (risk to the initial stop, the
position-sizing method) or --fixed-inr. The size is set on the signal close, capped by the cash
available at the fill, and rounded down to whole shares or whole --lot-size lots (futures, SME).
- Intraday turns each signal into a next-session open-to-close MIS trade.
- Shorts need
--segment futures --allow-short. An Indian cash-market short has to be bought
back the same session (SLB aside), so a multi-day short only exists as futures. Futures notional ≤
equity × --leverage. Rollover, basis and margin calls are not modelled.
- Circuits: with
--circuit-band 2|5|10|20, an open at the band limit gets no fill. The entry is
skipped; an exit or stop waits for the next unlocked open. Each case is listed under order events.
- Regime filter:
--regime-csv nifty.csv (or --regime-symbol NIFTY) allows longs only while the
benchmark closes above its --regime-ma (200) SMA on the signal day, and shorts only below it.
- Cash earns nothing. Sharpe and Sortino subtract
--rf (default 6.5% a year, about a liquid
fund or T-bill; change it).
--tax applies indian-tax-for-traders rates for a rough post-tax view: STCG 20% (held ≤12
months), LTCG 12.5% above ₹1.25 lakh per FY, intraday and futures at --slab-pct, plus 4% cess.
It is approximate: losses are not carried forward and STT is treated as deductible, which it is not.
Reading the output
- Versus buy-and-hold (delivery, one round trip). A rule earns its keep with a better Sharpe or
Calmar, or a much smaller drawdown, not just a higher return in a bull market.
- Max drawdown and longest underwater stretch: would you have kept following the rules through it?
- Profit factor (after charges) below 1.2 is thin. Above 2 on fewer than 30 trades is suspicious.
- Expectancy: about +0.2R or more after costs is worth a closer look. Breakeven trades (net ₹0)
count as neither wins nor losses and do not end a losing streak.
- Charges as % of gross profit above 25% means costs, not the market, own the result.
- Yearly table: one great year carrying the whole test is regime luck.
- Sweep: plateau (neighbours keep ≥75% of the best score) is what you want. Slope means pick
the middle of the good zone. Spike means curve-fit. The luck hurdle is the Sharpe the best of N
zero-edge variants would show by chance; the best cell should clear it comfortably.
- Walk-forward: efficiency = out-of-sample CAGR ÷ mean in-sample CAGR. ≥0.5 holds up; below 0
fails. Frequent parameter changes mean the "optimum" is noise.
- Monte Carlo: size for the 95th-percentile drawdown, not the backtest's one path. bootstrap
varies the outcome; shuffle only reorders the trades (final equity is fixed, the path is not).
Checklist: try to break the idea before it breaks your account
- Look-ahead: can every input be known before the order? Today's high/low or close cannot
trigger an entry today. Dividend-adjusted closes are not prices anyone traded at.
- Survivorship: today's NIFTY 50 or a current screener list are winners by construction. Ten
years on them flatters every long strategy. Add names that were dropped, delisted or merged, or
test the index itself.
- Overfitting: each extra grid cell is another lottery ticket. Keep grids coarse, insist on a
plateau, walk forward, and leave the last 1–2 years untouched until the very end.
- Costs: a delivery round trip at Zerodha costs about 0.24% of the position (STT 0.1% a side,
stamp duty, DP charge). 100 full-size round trips a year is about 24% of capital before any edge.
High-turnover ideas die here. Rerun at 2–3× slippage and on a costlier broker.
- Regime: does it only work in 2020–21-style rallies? Check the yearly rows, add
--regime-csv,
and include a bad phase (2008, 2015–16, 2018 small caps, March 2020, late 2024–early 2025).
- Data: Yahoo history usually adjusts splits and bonuses, but not always. Moves of 25% or more
overnight are flagged; check them. Dividends are left out for both the strategy and buy-and-hold.
- Small samples: under 30 trades is an anecdote. Run the same rules on several stocks and look
at the spread of results, not the best one.
- Execution: thin names lock at circuits and slip more (
--circuit-band, higher slippage). Stop
orders are DAY-only on exchanges, so a real system needs GTTs (see breakout-planner).
Workflow with other skills
market-regime (../market-regime/scripts/regime.py): test whether a NIFTY trend filter
(--regime-csv) cuts drawdown more than it cuts return before using it live.
- Run
run → sweep → walkforward → montecarlo, and stop at the first red flag.
position-sizing (../position-sizing/scripts/risk.py): choose a --risk-pct that keeps the Monte
Carlo 95th-percentile drawdown survivable.
trading-discipline: --trades-csv writes journal columns, so
python3 ../trading-discipline/scripts/discipline.py review t.csv breaks the backtest down by
weekday and setup. Compare it with your live journal later; a large gap is a warning.
breakout-planner: 52w-high and donchian-breakout are rough stand-ins for its Stage-2 entries.
They tell you whether breakout buying pays on a stock at all, not whether a given VCP will work.
Limits: one symbol and one position at a time (no portfolio rotation), daily or weekly bars, no
options, no tick rounding.
Output
NAME: strategy (params) | segment on NSE via broker | capital | sizing | slippage
start → end | bars (years) | signal on close, fill next open | charges as of <date>
Strategy vs Buy & hold: total return, CAGR, max DD, volatility, Sharpe (rf), Sortino, Calmar
Trades N: W / L / BE | win rate | avg win / loss | PF | expectancy ₹ (R) | payoff | losing streak
Exposure | avg hold | max DD dates | longest underwater | charges (% of gross profit) | slippage
Year table | last trades | order events | red flags | data notes
Educational analysis, not investment advice. A backtest describes the past, not your next trade.
1---2name: backtest-lab3description: |4 Backtests rule-based swing ideas on NSE/BSE daily bars with Indian frictions built in: decide on5 the close and fill at the next open, gap-through stops, slippage, exact per-trade charges by6 segment and broker (STT, stamp duty, GST, DP), whole shares or lots, circuit-band no-fills,7 futures-only shorts and an optional STCG/LTCG estimate. Six built-in strategies; CAGR vs8 buy-and-hold, drawdown, Sharpe/Sortino, profit factor, expectancy in ₹ and R; parameter sweeps9 with a plateau-or-spike read, walk-forward and Monte Carlo. backtest.py, stdlib only, offline.1011 Use when the user asks: "backtest this strategy", "would a 20/50 crossover have worked on X",12 "is this edge real or curve-fit", "optimise my parameters", "walk-forward test", "Monte Carlo my13 trades", "what drawdown should I expect", "do charges kill this idea", "does a NIFTY 200-DMA14 filter help", or before putting real money behind any mechanical rule.15metadata:16 source: https://skillmd.com/skills/majiayu000/backtest-lab17---1819# Backtest Lab2021A backtest cannot prove an idea works. It can show quickly that an idea does not. Judge a rule set22by how little it degrades when Indian charges, overnight gaps, unseen years and bad luck are piled23on, and treat a spectacular first run as a reason for suspicion.2425## Commands2627```bash28python3 scripts/backtest.py strategies # rules and defaults29python3 scripts/backtest.py run --csv tcs.csv --strategy sma-cross --params fast=20 slow=5030python3 scripts/backtest.py run --symbol POLYCAB --strategy 52w-high --risk-pct 1 --tax --trades-csv t.csv31python3 scripts/backtest.py run --csv hdfcbank.csv --strategy donchian-breakout --regime-csv nifty.csv32python3 scripts/backtest.py run --csv nifty.csv --strategy sma-cross --segment futures --lot-size 65 \33 --allow-short --leverage 3 --size-pct 30034python3 scripts/backtest.py sweep --csv tcs.csv --strategy sma-cross --grid fast=10,20,30 slow=50,100,20035python3 scripts/backtest.py walkforward --csv tcs.csv --strategy donchian-breakout \36 --grid entry_n=20,40,55 exit_n=10,20 --is-bars 756 --oos-bars 25237python3 scripts/backtest.py montecarlo --csv tcs.csv --strategy ema-pullback --sims 2000 --seed 738python3 scripts/backtest.py montecarlo --from-trades t.csv --ruin-dd 2539```40Inputs follow `technical-analysis`: `--csv`, `--candles` (broker-MCP JSON, null candles skipped) or41`--symbol` (yfinance, `--period 10y`). `--start` sets the first trading day while earlier bars still42warm up the indicators. `--grid` also takes ranges (`fast=10:50:10`). Every command takes `--json`.43Bad input exits 2 with one `error:` line.4445## Strategies (`--strategy`, override with `--params key=value`)4647| Name | Rule (long side; shorts mirror it) | Defaults |48|---|---|---|49| sma-cross | fast SMA crosses above slow; out when back below | fast 20, slow 50, stop 3×ATR |50| ema-pullback | close above a rising trend EMA, low tags the EMA, close back above it | ema 20, trend 100, 2×ATR, target 2R, 20 bars |51| **rsi-reversion** | RSI(period) below buy_below while above the trend SMA; out above sell_above | 2, 10, 70, trend 200, 10 bars |52| donchian-breakout | close above the prior entry_n high; out below the prior exit_n low | 20 / 10, 2×ATR |53| bollinger-reversion | close below the lower band; out at the middle band | 20, k 2, trend 0 (off), 20 bars |54| 52w-high | close above the prior lookback-bar high; out below the exit SMA | 252, exit_ma 50, 2.5×ATR |5556Every strategy also takes `stop_atr` (k × ATR14 from the fill), `stop_pct` (overrides it),57`target_r` and `max_hold` (bars), where 0 turns each one off. There is no custom-code hook: new58rules are added to the script as reviewed code.5960## How orders and costs are simulated6162- **No look-ahead.** Signals use bars up to and including the signal bar's close. The order fills at63 the next bar's open, never at the close that produced it.64- **Stops and targets** rest in the market. A gap through the level fills at the open (a stop at ₹10165 after a ₹96 open books ₹96). If one bar touches both, the stop is assumed to have filled first.66- **Slippage** `--slippage-bps` (default 5) on every fill. Use 15–30 for small caps.67- **Charges** come from `trading-costs` (charges.py) for each round trip, by `--segment68 delivery|intraday|futures` and `--broker`. A delivery buy sold the same day is charged as intraday.69- **Sizing**: `--size-pct` (default 100% of equity), `--risk-pct` (risk to the initial stop, the70 `position-sizing` method) or `--fixed-inr`. The size is set on the signal close, capped by the cash71 available at the fill, and rounded down to whole shares or whole `--lot-size` lots (futures, SME).72- **Intraday** turns each signal into a next-session open-to-close MIS trade.73- **Shorts** need `--segment futures --allow-short`. An Indian cash-market short has to be bought74 back the same session (SLB aside), so a multi-day short only exists as futures. Futures notional ≤75 equity × `--leverage`. Rollover, basis and margin calls are not modelled.76- **Circuits**: with `--circuit-band 2|5|10|20`, an open at the band limit gets no fill. The entry is77 skipped; an exit or stop waits for the next unlocked open. Each case is listed under order events.78- **Regime filter**: `--regime-csv nifty.csv` (or `--regime-symbol NIFTY`) allows longs only while the79 benchmark closes above its `--regime-ma` (200) SMA on the signal day, and shorts only below it.80- **Cash** earns nothing. Sharpe and Sortino subtract `--rf` (default 6.5% a year, about a liquid81 fund or T-bill; change it).82- **`--tax`** applies `indian-tax-for-traders` rates for a rough post-tax view: STCG 20% (held ≤1283 months), LTCG 12.5% above ₹1.25 lakh per FY, intraday and futures at `--slab-pct`, plus 4% cess.84 It is approximate: losses are not carried forward and STT is treated as deductible, which it is not.8586## Reading the output8788- **Versus buy-and-hold** (delivery, one round trip). A rule earns its keep with a better Sharpe or89 Calmar, or a much smaller drawdown, not just a higher return in a bull market.90- **Max drawdown and longest underwater stretch**: would you have kept following the rules through it?91- **Profit factor** (after charges) below 1.2 is thin. Above 2 on fewer than 30 trades is suspicious.92- **Expectancy**: about +0.2R or more after costs is worth a closer look. Breakeven trades (net ₹0)93 count as neither wins nor losses and do not end a losing streak.94- **Charges as % of gross profit** above 25% means costs, not the market, own the result.95- **Yearly table**: one great year carrying the whole test is regime luck.96- **Sweep**: *plateau* (neighbours keep ≥75% of the best score) is what you want. *Slope* means pick97 the middle of the good zone. *Spike* means curve-fit. The luck hurdle is the Sharpe the best of N98 zero-edge variants would show by chance; the best cell should clear it comfortably.99- **Walk-forward**: efficiency = out-of-sample CAGR ÷ mean in-sample CAGR. ≥0.5 holds up; below 0100 fails. Frequent parameter changes mean the "optimum" is noise.101- **Monte Carlo**: size for the 95th-percentile drawdown, not the backtest's one path. *bootstrap*102 varies the outcome; *shuffle* only reorders the trades (final equity is fixed, the path is not).103104## Checklist: try to break the idea before it breaks your account1051061. **Look-ahead**: can every input be known before the order? Today's high/low or close cannot107 trigger an entry today. Dividend-adjusted closes are not prices anyone traded at.1082. **Survivorship**: today's NIFTY 50 or a current screener list are winners by construction. Ten109 years on them flatters every long strategy. Add names that were dropped, delisted or merged, or110 test the index itself.1113. **Overfitting**: each extra grid cell is another lottery ticket. Keep grids coarse, insist on a112 plateau, walk forward, and leave the last 1–2 years untouched until the very end.1134. **Costs**: a delivery round trip at Zerodha costs about 0.24% of the position (STT 0.1% a side,114 stamp duty, DP charge). 100 full-size round trips a year is about 24% of capital before any edge.115 High-turnover ideas die here. Rerun at 2–3× slippage and on a costlier broker.1165. **Regime**: does it only work in 2020–21-style rallies? Check the yearly rows, add `--regime-csv`,117 and include a bad phase (2008, 2015–16, 2018 small caps, March 2020, late 2024–early 2025).1186. **Data**: Yahoo history usually adjusts splits and bonuses, but not always. Moves of 25% or more119 overnight are flagged; check them. Dividends are left out for both the strategy and buy-and-hold.1207. **Small samples**: under 30 trades is an anecdote. Run the same rules on several stocks and look121 at the spread of results, not the best one.1228. **Execution**: thin names lock at circuits and slip more (`--circuit-band`, higher slippage). Stop123 orders are DAY-only on exchanges, so a real system needs GTTs (see `breakout-planner`).124125## Workflow with other skills1261271. `market-regime` (../market-regime/scripts/regime.py): test whether a NIFTY trend filter128 (`--regime-csv`) cuts drawdown more than it cuts return before using it live.1292. Run `run` → `sweep` → `walkforward` → `montecarlo`, and stop at the first red flag.1303. `position-sizing` (../position-sizing/scripts/risk.py): choose a `--risk-pct` that keeps the Monte131 Carlo 95th-percentile drawdown survivable.1324. `trading-discipline`: `--trades-csv` writes journal columns, so133 `python3 ../trading-discipline/scripts/discipline.py review t.csv` breaks the backtest down by134 weekday and setup. Compare it with your live journal later; a large gap is a warning.1355. `breakout-planner`: 52w-high and donchian-breakout are rough stand-ins for its Stage-2 entries.136 They tell you whether breakout buying pays on a stock at all, not whether a given VCP will work.137138Limits: one symbol and one position at a time (no portfolio rotation), daily or weekly bars, no139options, no tick rounding.140141## Output142143```144NAME: strategy (params) | segment on NSE via broker | capital | sizing | slippage145start → end | bars (years) | signal on close, fill next open | charges as of <date>146Strategy vs Buy & hold: total return, CAGR, max DD, volatility, Sharpe (rf), Sortino, Calmar147Trades N: W / L / BE | win rate | avg win / loss | PF | expectancy ₹ (R) | payoff | losing streak148Exposure | avg hold | max DD dates | longest underwater | charges (% of gross profit) | slippage149Year table | last trades | order events | red flags | data notes150```151152_Educational analysis, not investment advice. A backtest describes the past, not your next trade._