KOSPI Backtest Dashboard

run_id: 20260320T091531Z_userreq_toss_full_tabm_256_alpha101_20260320_target350_z0p1
generated_at_utc: 2026-03-20T09:15:59.878559+00:00

Top KPI

trade_return_per_trade_bp = (total_pnl_final / total_trade_notional) * 10000
metric value
total_pnl_final 24.720M
total_trade_notional 105331.771M
daily_trade_notional 2569.068M
total_fee 105.332M
mdd_pnl -8.884M
alpha_vs_dynamic_notional_beta_pnl_final 14.954M
alpha_vs_avg_hold_notional_beta_pnl_final 14.562M
dynamic_alpha_mdd_pnl -4.415M
avg_hold_alpha_mdd_pnl -4.650M
dynamic_alpha_sharpe_annualized 5.73897
avg_hold_alpha_sharpe_annualized 5.50739
time_avg_total_notional_position_usdt 91.198M
time_avg_high_mc_notional_position_usdt 0.000M
time_avg_low_mc_notional_position_usdt 91.198M
trade_return_per_trade_bp 2.35bp
roi_avg_notional_position_pct 27.11%
roi_peak_notional_position_pct 24.62%
num_trades 46,398
high_mc_trade_notional 0.000M
high_mc_sharpe_annualized
high_mc_trade_return_per_trade_bp
low_mc_trade_notional 105331.771M
low_mc_sharpe_annualized 9.41181
low_mc_trade_return_per_trade_bp 2.35bp
sharpe_annualized 9.41181

Run Parameters

source: not_found
param value
active_minutes_ratio 0.5
confidence_median_adjust_multiplier 1
force_hedge_timeout_window 300
force_taker_start_hhmm 1540
hedge_max_amount_krw 2.5e+06
hedge_pred_threshold 0
hedge_slippage 0
high_speed 1
model_slippage 0
one_coin_max_neg_position_krw 0
one_coin_max_pos_position_krw 2.5e+06
position_close_timeout_minutes 120
pred_sma_len 1
total_max_abs_position_krw 1e+08
trade_end_hhmm 1520
trade_start_hhmm 905
z_score_threshold 0.1
z_score_time_window 120

Core KPI

roi_avg_notional_position_pct = total_pnl_final / time_avg_abs_net_position_usdt * 100
roi_peak_notional_position_pct = total_pnl_final / peak_abs_net_position_usdt * 100
dynamic_notional_beta = cumsum(total_notional_position_usdt(t) * mean(close c2c return across all coins at t))
avg_hold_notional_beta = cumsum(avg_total_notional_position_usdt * mean(close c2c return across all coins at t))
high/low dynamic_notional_beta = cumsum(segment_notional_position_usdt(t) * mean(close c2c return in each segment at t))
high/low avg_hold_notional_beta = cumsum(avg_segment_notional_position_usdt * mean(close c2c return in each segment at t))
alpha_vs_dynamic = pnl - dynamic_notional_beta, alpha_vs_avg_hold = pnl - avg_hold_notional_beta
dynamic_alpha_mdd_pnl / avg_hold_alpha_mdd_pnl = min(alpha - cummax(alpha)) on each alpha series
dynamic_alpha_sharpe_annualized / avg_hold_alpha_sharpe_annualized = mean(Δalpha) / std(Δalpha) * sqrt(252 * 390)
mdd_pnl = min(total_pnl - cummax(total_pnl))
sharpe_annualized = mean(Δpnl) / std(Δpnl) * sqrt(252 * 390)
total_fee = sum(execution fee)
metric value
total_pnl_final 24.720M
total_pnl_peak 26.107M
dynamic_notional_beta_pnl_final 9.766M
alpha_vs_dynamic_notional_beta_pnl_final 14.954M
avg_hold_notional_beta_pnl_final 10.159M
alpha_vs_avg_hold_notional_beta_pnl_final 14.562M
high_mc_dynamic_notional_beta_pnl_final 0.000M
low_mc_dynamic_notional_beta_pnl_final 9.766M
high_mc_avg_hold_notional_beta_pnl_final 0.000M
low_mc_avg_hold_notional_beta_pnl_final 10.159M
high_mc_alpha_vs_dynamic_notional_beta_pnl_final 0.000M
low_mc_alpha_vs_dynamic_notional_beta_pnl_final 14.954M
high_mc_alpha_vs_avg_hold_notional_beta_pnl_final 0.000M
low_mc_alpha_vs_avg_hold_notional_beta_pnl_final 14.562M
dynamic_alpha_mdd_pnl -4.415M
dynamic_alpha_sharpe_annualized 5.73897
avg_hold_alpha_mdd_pnl -4.650M
avg_hold_alpha_sharpe_annualized 5.50739
num_trades 46,398
total_traded_amount_sum 5.55965e+07
total_trade_notional 105331.771M
daily_trade_notional 2569.068M
trading_day_count 41
total_fee 105.332M
time_avg_total_notional_position_usdt 91.198M
time_avg_high_mc_notional_position_usdt 0.000M
time_avg_low_mc_notional_position_usdt 91.198M
time_avg_net_position_usdt 91.198M
time_avg_abs_net_position_usdt 91.198M
peak_abs_net_position_usdt 1.00428e+08
roi_avg_notional_position_pct 27.11%
roi_peak_notional_position_pct 24.62%
mdd_pnl -8.884M
sharpe_annualized 9.41181
high_mc_pnl_final 0.000M
high_mc_trade_notional 0.000M
high_mc_num_trades 0
high_mc_sharpe_annualized
high_mc_trade_return_per_trade_bp
low_mc_pnl_final 24.720M
low_mc_trade_notional 105331.771M
low_mc_num_trades 46,398
low_mc_sharpe_annualized 9.41181
low_mc_trade_return_per_trade_bp 2.35bp
model_zscore_pnl_final 17981.429M
hedge_zscore_pnl_final 0.022M
force_zscore_pnl_final 0.000M
funding_fee_pnl_final 0.000M
funding_event_count 0
model_win_rate_20m 50.74%
hedge_win_rate_20m 100.00%
force_win_rate_20m
model_win_rate_btc_adj_20m 50.74%
hedge_win_rate_btc_adj_20m 100.00%
force_win_rate_btc_adj_20m

MC Segment KPI

segment in [total, high, low] computed by the same metric function over coin subsets
trade_return_per_trade_bp = pnl_final / trade_notional * 10000
segment pnl_final trade_notional num_trades sharpe_annualized trade_return_per_trade_bp
total 2.47205e+07 1.05332e+11 46398 9.41181 2.34692
high 0 0 0
low 2.47205e+07 1.05332e+11 46398 9.41181 2.34692

Quality By Horizon (Model)

quality = side_sign * (mid_price(next_n_bars) - execution_price) / execution_price - (fee / notional)
quality_btc_adj = quality - side_sign * ((btc_mid(t+n) - btc_mid(t)) / btc_mid(t))
quality_per_notional = quality_pnl / sum(notional_usdt)
quality_per_notional_bp = quality_per_notional * 10000
n_min pair_count quality_pnl_final quality_per_notional quality_per_notional_bp win_rate reg_a reg_b reg_r2 quality_btc_adj_pnl_final quality_btc_adj_per_notional quality_btc_adj_per_notional_bp win_rate_btc_adj
5 46396 165151 1.56799e-06 0.0156799 0.471226 0.00681395 -0.00117486 0.0189529 165151 1.56799e-06 0.0156799 0.471226
10 46396 8.64305e+06 8.20593e-05 0.820593 0.498427 0.00767771 -0.00124608 0.0188082 8.64305e+06 8.20593e-05 0.820593 0.498427
20 46330 8.55666e+06 8.13531e-05 0.813531 0.507382 0.00840175 -0.00136055 0.0116847 8.55666e+06 8.13531e-05 0.813531 0.507382
30 46249 1.00568e+07 9.57691e-05 0.957691 0.511925 0.00886593 -0.00141709 0.00798487 1.00568e+07 9.57691e-05 0.957691 0.511925
60 46035 1.55858e+07 0.000149099 1.49099 0.512284 0.00938956 -0.00142504 0.00439972 1.55858e+07 0.000149099 1.49099 0.512284
120 45602 1.58179e+07 0.000152679 1.52679 0.509122 0.0101409 -0.00153819 0.00284782 1.58179e+07 0.000152679 1.52679 0.509122
240 44564 1.99858e+07 0.000197407 1.97407 0.507428 0.00955818 -0.001382 0.00123684 1.99858e+07 0.000197407 1.97407 0.507428

Quality By Horizon (Hedge)

n_min pair_count quality_pnl_final quality_per_notional quality_per_notional_bp win_rate reg_a reg_b reg_r2 quality_btc_adj_pnl_final quality_btc_adj_per_notional quality_btc_adj_per_notional_bp win_rate_btc_adj
5 2 6365.62 0.00129636 12.9636 1 0.276227 -0.000208761 1 6365.62 0.00129636 12.9636 1
10 2 4807.62 0.000979073 9.79073 0.5 0.362584 -0.000996593 1 4807.62 0.000979073 9.79073 0.5
20 2 41381.6 0.00842738 84.2738 1 0.137828 0.00767637 1 41381.6 0.00842738 84.2738 1
30 2 12227.6 0.00249016 24.9016 0.5 -0.949924 0.00766615 1 12227.6 0.00249016 24.9016 0.5
60 2 47243.6 0.00962117 96.2117 1 -1.08832 0.0155513 1 47243.6 0.00962117 96.2117 1
120 2 96651.6 0.0196831 196.831 1 -1.12321 0.0258033 1 96651.6 0.0196831 196.831 1
240 2 68831.6 0.0140176 140.176 1 -0.933053 0.0191016 1 68831.6 0.0140176 140.176 1

Quality By Horizon (Force)

n_min pair_count quality_pnl_final quality_per_notional quality_per_notional_bp win_rate reg_a reg_b reg_r2 quality_btc_adj_pnl_final quality_btc_adj_per_notional quality_btc_adj_per_notional_bp win_rate_btc_adj
5 0 0 NaN NaN NaN 0 0 0 0 NaN NaN NaN
10 0 0 NaN NaN NaN 0 0 0 0 NaN NaN NaN
20 0 0 NaN NaN NaN 0 0 0 0 NaN NaN NaN
30 0 0 NaN NaN NaN 0 0 0 0 NaN NaN NaN
60 0 0 NaN NaN NaN 0 0 0 0 NaN NaN NaN
120 0 0 NaN NaN NaN 0 0 0 0 NaN NaN NaN
240 0 0 NaN NaN NaN 0 0 0 0 NaN NaN NaN

PnL / Exposure

Model Buy 120m Relative Quality By Entry Time (20m, 09:00-15:30 KST)

quality_120m_mean = average of quality_120m for tag=model_buy in each 20-minute entry-time bucket
quality_120m_mean_bp = quality_120m_mean * 10000, total_amount = sum(abs(amount))
entry_time_bucket trade_count total_amount quality_120m_mean quality_120m_mean_bp
09:00 1528 1.26221e+06 0.000284346 2.84346
09:20 1812 1.81968e+06 0.00166019 16.6019
09:40 1411 1.79422e+06 0.00141216 14.1216
10:00 1319 1.70205e+06 0.00115648 11.5648
10:20 1177 1.72775e+06 0.00217219 21.7219
10:40 1245 1.66638e+06 0.00178172 17.8172
11:00 1327 1.69224e+06 0.00138519 13.8519
11:20 1220 1.61481e+06 0.00219183 21.9183
11:40 1176 1.56822e+06 0.00267556 26.7556
12:00 1147 1.45456e+06 0.00215699 21.5699
12:20 1177 1.57882e+06 0.00273875 27.3875
12:40 1376 1.75601e+06 0.00152522 15.2522
13:00 1290 1.35744e+06 0.00119124 11.9124
13:20 1017 1.13526e+06 0.00262326 26.2326
13:40 831 649717 0.00281661 28.1661
14:00 881 743723 0.00378433 37.8433
14:20 825 782198 0.00206255 20.6255
14:40 1192 1.46601e+06 0.00333475 33.3475
15:00 1632 2.04302e+06 0.00244255 24.4255
15:20 0 0

Z-Score-Quality Scatter + Regression

Model Buy/Sell Scatter + Regression