KOSPI Backtest Dashboard

run_id: 20260320T091451Z_userreq_toss_full_tabm_256_alpha101_20260320_target350_z0p2
generated_at_utc: 2026-03-20T09:15:30.323469+00:00

Top KPI

trade_return_per_trade_bp = (total_pnl_final / total_trade_notional) * 10000
metric value
total_pnl_final 30.716M
total_trade_notional 87894.406M
daily_trade_notional 2143.766M
total_fee 87.894M
mdd_pnl -8.045M
alpha_vs_dynamic_notional_beta_pnl_final 20.257M
alpha_vs_avg_hold_notional_beta_pnl_final 20.416M
dynamic_alpha_mdd_pnl -4.587M
avg_hold_alpha_mdd_pnl -4.651M
dynamic_alpha_sharpe_annualized 7.61982
avg_hold_alpha_sharpe_annualized 7.62492
time_avg_total_notional_position_usdt 92.463M
time_avg_high_mc_notional_position_usdt 0.000M
time_avg_low_mc_notional_position_usdt 92.463M
trade_return_per_trade_bp 3.49bp
roi_avg_notional_position_pct 33.22%
roi_peak_notional_position_pct 30.39%
num_trades 39,169
high_mc_trade_notional 0.000M
high_mc_sharpe_annualized
high_mc_trade_return_per_trade_bp
low_mc_trade_notional 87894.406M
low_mc_sharpe_annualized 11.5759
low_mc_trade_return_per_trade_bp 3.49bp
sharpe_annualized 11.5759

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 0.2
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 30.716M
total_pnl_peak 31.586M
dynamic_notional_beta_pnl_final 10.459M
alpha_vs_dynamic_notional_beta_pnl_final 20.257M
avg_hold_notional_beta_pnl_final 10.300M
alpha_vs_avg_hold_notional_beta_pnl_final 20.416M
high_mc_dynamic_notional_beta_pnl_final 0.000M
low_mc_dynamic_notional_beta_pnl_final 10.459M
high_mc_avg_hold_notional_beta_pnl_final 0.000M
low_mc_avg_hold_notional_beta_pnl_final 10.300M
high_mc_alpha_vs_dynamic_notional_beta_pnl_final 0.000M
low_mc_alpha_vs_dynamic_notional_beta_pnl_final 20.257M
high_mc_alpha_vs_avg_hold_notional_beta_pnl_final 0.000M
low_mc_alpha_vs_avg_hold_notional_beta_pnl_final 20.416M
dynamic_alpha_mdd_pnl -4.587M
dynamic_alpha_sharpe_annualized 7.61982
avg_hold_alpha_mdd_pnl -4.651M
avg_hold_alpha_sharpe_annualized 7.62492
num_trades 39,169
total_traded_amount_sum 4.85043e+07
total_trade_notional 87894.406M
daily_trade_notional 2143.766M
trading_day_count 41
total_fee 87.894M
time_avg_total_notional_position_usdt 92.463M
time_avg_high_mc_notional_position_usdt 0.000M
time_avg_low_mc_notional_position_usdt 92.463M
time_avg_net_position_usdt 92.463M
time_avg_abs_net_position_usdt 92.463M
peak_abs_net_position_usdt 1.01081e+08
roi_avg_notional_position_pct 33.22%
roi_peak_notional_position_pct 30.39%
mdd_pnl -8.045M
sharpe_annualized 11.5759
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 30.716M
low_mc_trade_notional 87894.406M
low_mc_num_trades 39,169
low_mc_sharpe_annualized 11.5759
low_mc_trade_return_per_trade_bp 3.49bp
model_zscore_pnl_final 15980.026M
hedge_zscore_pnl_final 0.373M
force_zscore_pnl_final 0.000M
funding_fee_pnl_final 0.000M
funding_event_count 0
model_win_rate_20m 51.70%
hedge_win_rate_20m 75.00%
force_win_rate_20m
model_win_rate_btc_adj_20m 51.70%
hedge_win_rate_btc_adj_20m 75.00%
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 3.07159e+07 8.78944e+10 39169 11.5759 3.49463
high 0 0 0
low 3.07159e+07 8.78944e+10 39169 11.5759 3.49463

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 39161 6.5325e+06 7.43385e-05 0.743385 0.478205 0.00659049 -0.0011311 0.0169365 6.5325e+06 7.43385e-05 0.743385 0.478205
10 39161 1.48723e+07 0.000169243 1.69243 0.506167 0.00739162 -0.0011837 0.0170842 1.48723e+07 0.000169243 1.69243 0.506167
20 39114 1.66513e+07 0.000189714 1.89714 0.51695 0.00813143 -0.00130103 0.0110591 1.66513e+07 0.000189714 1.89714 0.51695
30 39041 1.69803e+07 0.000193747 1.93747 0.516918 0.00867142 -0.00138705 0.00728689 1.69803e+07 0.000193747 1.93747 0.516918
60 38849 2.26661e+07 0.000259815 2.59815 0.517259 0.0092296 -0.00139464 0.00423278 2.26661e+07 0.000259815 2.59815 0.517259
120 38503 2.18961e+07 0.000253079 2.53079 0.512687 0.010482 -0.00161681 0.00299148 2.18961e+07 0.000253079 2.53079 0.512687
240 37775 2.53791e+07 0.000298929 2.98929 0.510311 0.00912913 -0.00129892 0.00111044 2.53791e+07 0.000298929 2.98929 0.510311

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 8 -783.667 -4.04877e-05 -0.404877 0.5 0.00537124 -0.000251685 0.000372478 -783.667 -4.04877e-05 -0.404877 0.5
10 8 45868.3 0.00236976 23.6976 0.625 -0.0208507 0.00270119 0.00400252 45868.3 0.00236976 23.6976 0.625
20 8 96179.3 0.00496905 49.6905 0.75 -0.144448 0.00778908 0.169017 96179.3 0.00496905 49.6905 0.75
30 8 59417.3 0.00306976 30.6976 0.625 -0.0366011 0.00370266 0.00991601 59417.3 0.00306976 30.6976 0.625
60 8 118175 0.00610546 61.0546 0.75 -0.0974012 0.00792029 0.0310935 118175 0.00610546 61.0546 0.75
120 8 201316 0.0104009 104.009 0.875 -0.356071 0.0174774 0.240971 201316 0.0104009 104.009 0.875
240 8 200452 0.0103563 103.563 0.875 0.071636 0.00870577 0.0150598 200452 0.0103563 103.563 0.875

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 1280 1.06362e+06 0.000236508 2.36508
09:20 1533 1.5473e+06 0.00158625 15.8625
09:40 1182 1.47387e+06 0.00172816 17.2816
10:00 1089 1.38911e+06 0.00145619 14.5619
10:20 959 1.49548e+06 0.00239035 23.9035
10:40 995 1.32221e+06 0.00202898 20.2898
11:00 1098 1.42991e+06 0.00117666 11.7666
11:20 985 1.43229e+06 0.00217509 21.7509
11:40 949 1.33642e+06 0.00267819 26.7819
12:00 930 1.23302e+06 0.00216773 21.6773
12:20 947 1.31532e+06 0.00255725 25.5725
12:40 1174 1.55934e+06 0.00173907 17.3907
13:00 1097 1.22248e+06 0.00132015 13.2015
13:20 946 1.09436e+06 0.00318231 31.8231
13:40 800 652760 0.00286307 28.6307
14:00 769 653280 0.00332184 33.2184
14:20 780 814139 0.00282055 28.2055
14:40 1051 1.43041e+06 0.0017461 17.461
15:00 1396 1.80383e+06 0.00344431 34.4431
15:20 0 0

Z-Score-Quality Scatter + Regression

Model Buy/Sell Scatter + Regression