KOSPI Backtest Dashboard

run_id: 20260321T111227Z_userreq_toss_tabm_enh129_ceonly_20260320_target350_z0p5
generated_at_utc: 2026-03-21T11:14:51.014590+00:00

Top KPI

trade_return_per_trade_bp = (total_pnl_final / total_trade_notional) * 10000
metric value
total_pnl_final 42.407M
total_trade_notional 57011.959M
daily_trade_notional 1390.536M
total_fee 57.012M
mdd_pnl -8.385M
alpha_vs_dynamic_notional_beta_pnl_final 30.781M
alpha_vs_avg_hold_notional_beta_pnl_final 31.727M
dynamic_alpha_mdd_pnl -2.293M
avg_hold_alpha_mdd_pnl -2.310M
dynamic_alpha_sharpe_annualized 11.8462
avg_hold_alpha_sharpe_annualized 12.3326
time_avg_total_notional_position_usdt 95.879M
time_avg_high_mc_notional_position_usdt 0.000M
time_avg_low_mc_notional_position_usdt 95.879M
trade_return_per_trade_bp 7.44bp
roi_avg_notional_position_pct 44.23%
roi_peak_notional_position_pct 40.42%
num_trades 27,367
high_mc_trade_notional 0.000M
high_mc_sharpe_annualized
high_mc_trade_return_per_trade_bp
low_mc_trade_notional 57011.959M
low_mc_sharpe_annualized 11.9161
low_mc_trade_return_per_trade_bp 7.44bp
sharpe_annualized 11.9161

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 0.5
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 42.407M
total_pnl_peak 42.477M
dynamic_notional_beta_pnl_final 11.626M
alpha_vs_dynamic_notional_beta_pnl_final 30.781M
avg_hold_notional_beta_pnl_final 10.680M
alpha_vs_avg_hold_notional_beta_pnl_final 31.727M
high_mc_dynamic_notional_beta_pnl_final 0.000M
low_mc_dynamic_notional_beta_pnl_final 11.626M
high_mc_avg_hold_notional_beta_pnl_final 0.000M
low_mc_avg_hold_notional_beta_pnl_final 10.680M
high_mc_alpha_vs_dynamic_notional_beta_pnl_final 0.000M
low_mc_alpha_vs_dynamic_notional_beta_pnl_final 30.781M
high_mc_alpha_vs_avg_hold_notional_beta_pnl_final 0.000M
low_mc_alpha_vs_avg_hold_notional_beta_pnl_final 31.727M
dynamic_alpha_mdd_pnl -2.293M
dynamic_alpha_sharpe_annualized 11.8462
avg_hold_alpha_mdd_pnl -2.310M
avg_hold_alpha_sharpe_annualized 12.3326
num_trades 27,367
total_traded_amount_sum 2.86573e+07
total_trade_notional 57011.959M
daily_trade_notional 1390.536M
trading_day_count 41
total_fee 57.012M
time_avg_total_notional_position_usdt 95.879M
time_avg_high_mc_notional_position_usdt 0.000M
time_avg_low_mc_notional_position_usdt 95.879M
time_avg_net_position_usdt 95.879M
time_avg_abs_net_position_usdt 95.879M
peak_abs_net_position_usdt 1.04918e+08
roi_avg_notional_position_pct 44.23%
roi_peak_notional_position_pct 40.42%
mdd_pnl -8.385M
sharpe_annualized 11.9161
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 42.407M
low_mc_trade_notional 57011.959M
low_mc_num_trades 27,367
low_mc_sharpe_annualized 11.9161
low_mc_trade_return_per_trade_bp 7.44bp
model_zscore_pnl_final 21599.265M
hedge_zscore_pnl_final 0.018M
force_zscore_pnl_final 0.000M
funding_fee_pnl_final 0.000M
funding_event_count 0
model_win_rate_20m 52.44%
hedge_win_rate_20m 100.00%
force_win_rate_20m
model_win_rate_btc_adj_20m 52.44%
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 4.24069e+07 5.7012e+10 27367 11.9161 7.43825
high 0 0 0
low 4.24069e+07 5.7012e+10 27367 11.9161 7.43825

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 27366 1.25029e+07 0.000219304 2.19304 0.490791 0.00184504 -0.000517588 0.00349664 1.25029e+07 0.000219304 2.19304 0.490791
10 27366 1.71904e+07 0.000301524 3.01524 0.510889 0.00238106 -0.000653937 0.00357367 1.71904e+07 0.000301524 3.01524 0.510889
20 27344 2.41265e+07 0.000423539 4.23539 0.524356 0.00321444 -0.00084425 0.00429365 2.41265e+07 0.000423539 4.23539 0.524356
30 27305 2.20836e+07 0.000388218 3.88218 0.52917 0.00425411 -0.00125753 0.00436014 2.20836e+07 0.000388218 3.88218 0.52917
60 27257 2.71933e+07 0.000478815 4.78815 0.52559 0.004918 -0.00140808 0.00359036 2.71933e+07 0.000478815 4.78815 0.52559
120 27217 3.54737e+07 0.000625538 6.25538 0.524599 0.00349446 -0.000692443 0.000974125 3.54737e+07 0.000625538 6.25538 0.524599
240 27143 4.01011e+07 0.000708666 7.08666 0.517887 0.00699689 -0.00191241 0.0017368 4.01011e+07 0.000708666 7.08666 0.517887

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 1 -125.04 -0.001 -10 0 0 0 0 -125.04 -0.001 -10 0
10 1 -125.04 -0.001 -10 0 0 0 0 -125.04 -0.001 -10 0
20 1 34.96 0.000279591 2.79591 1 0 0 0 34.96 0.000279591 2.79591 1
30 1 114.96 0.000919386 9.19386 1 0 0 0 114.96 0.000919386 9.19386 1
60 1 114.96 0.000919386 9.19386 1 0 0 0 114.96 0.000919386 9.19386 1
120 1 -45.04 -0.000360205 -3.60205 0 0 0 0 -45.04 -0.000360205 -3.60205 0
240 1 3394.96 0.027151 271.51 1 0 0 0 3394.96 0.027151 271.51 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 1213 1.32605e+06 0.00108728 10.8728
09:20 1145 1.01674e+06 0.00091703 9.1703
09:40 1005 922715 0.00118487 11.8487
10:00 901 1.0157e+06 0.0011736 11.736
10:20 787 802802 0.00149846 14.9846
10:40 759 789714 0.0022504 22.504
11:00 871 1.02482e+06 0.00160499 16.0499
11:20 913 1.21106e+06 0.0022753 22.753
11:40 924 1.06425e+06 0.00206941 20.6941
12:00 838 891046 0.00211413 21.1413
12:20 717 882341 0.00132959 13.2959
12:40 767 828688 0.00183706 18.3706
13:00 733 852690 0.000969454 9.69454
13:20 725 522016 0.0020987 20.987
13:40 422 257848 0.00126933 12.6933
14:00 366 182465 0.000655889 6.55889
14:20 390 218550 0.000784974 7.84974
14:40 440 177449 0.00801761 80.1761
15:00 588 354678 0.00367233 36.7233
15:20 0 0

Z-Score-Quality Scatter + Regression

Model Buy/Sell Scatter + Regression