finish experiment 46 (exp/46-q15-the-5-seed-rankicensemblelgbmodel-sh)
This commit is contained in:
zhaoli
@@ -0,0 +1,105 @@
|
||||
# QUEUE-12 — Long-horizon label (22d) + weekly recompute construction.
|
||||
# Untested combination from book/CLAIMS.md open questions: Q05 (exp 37) proved the
|
||||
# 22d label has the strongest signal (IC 0.097, RankIC 0.117) but daily turnover
|
||||
# killed the book (net -4.60%); Q07 (exp 39) proved weekly recompute is the cost
|
||||
# lever (net +12.51%). Hypothesis: pairing them monetizes the label edge.
|
||||
# Change vs exp-26 reference: label 5d -> 22d AND strategy -> WeeklyRebalanceDropoutStrategy.
|
||||
# Acceptance: net_IR > 0.5, net_ann > +5%, cost drag <= 2pp.
|
||||
# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q12_label22d_weekly.yaml \
|
||||
# experiment_name=tac-rd-q12-label22d-weekly
|
||||
{%- set LAKE = TAC_LAKE_DIR %}
|
||||
{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
|
||||
{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
|
||||
|
||||
qlib_init:
|
||||
provider_uri: "{{ LAKE }}"
|
||||
region: us
|
||||
expression_cache: null
|
||||
dataset_cache: null
|
||||
calendar_provider:
|
||||
class: tac_qlib.data.providers.LakeCalendarProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||
instrument_provider:
|
||||
class: tac_qlib.data.providers.LakeInstrumentProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
||||
feature_provider:
|
||||
class: tac_qlib.data.providers.LakeFeatureProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||
exp_manager:
|
||||
class: MLflowExpManager
|
||||
module_path: qlib.workflow.expm
|
||||
kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q12-label22d-weekly" }
|
||||
|
||||
task:
|
||||
model:
|
||||
class: RankICEnsembleLGBModel
|
||||
module_path: tac_qlib.contrib.model.rank_ensemble
|
||||
kwargs:
|
||||
loss: mse
|
||||
learning_rate: 0.02
|
||||
num_leaves: 31
|
||||
n_estimators: 3000
|
||||
num_boost_round: 3000
|
||||
early_stopping_rounds: 200
|
||||
min_data_in_leaf: 20
|
||||
lambda_l2: 0.5
|
||||
colsample_bytree: 0.8
|
||||
subsample: 0.8
|
||||
subsample_freq: 1
|
||||
reg_alpha: 0.1
|
||||
reg_lambda: 1.0
|
||||
seeds: "42,7,2026,99,123"
|
||||
|
||||
dataset:
|
||||
class: DatasetH
|
||||
module_path: qlib.data.dataset
|
||||
kwargs:
|
||||
handler:
|
||||
class: TACHandler
|
||||
module_path: tac_qlib.contrib.data.handler
|
||||
kwargs:
|
||||
instruments: "{{ UNIVERSE }}"
|
||||
start_time: 2015-01-03
|
||||
end_time: 2026-08-10
|
||||
fit_start_time: 2016-01-04
|
||||
fit_end_time: 2025-09-01
|
||||
freq: day
|
||||
lake_root: "{{ LAKE }}"
|
||||
market: US
|
||||
label: "Ref($close,-23)/Ref($close,-1)-1"
|
||||
feature_fields: "{{ FEATURES }}"
|
||||
infer_processors:
|
||||
- { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
||||
- { class: ProcessInf, kwargs: {} }
|
||||
- { class: CSRankNorm, kwargs: {} }
|
||||
- { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
||||
- { class: Fillna, kwargs: {} }
|
||||
segments:
|
||||
train: [2016-01-04, 2025-09-01]
|
||||
valid: [2025-09-03, 2026-01-03]
|
||||
test: [2026-01-04, 2026-08-10]
|
||||
|
||||
record:
|
||||
- { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
|
||||
- { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
|
||||
- class: PortAnaRecord
|
||||
module_path: qlib.workflow.record_temp
|
||||
kwargs:
|
||||
config:
|
||||
strategy:
|
||||
class: WeeklyRebalanceDropoutStrategy
|
||||
module_path: tac_qlib.contrib.strategy.weekly_rebalance
|
||||
kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
|
||||
backtest:
|
||||
start_time: 2026-01-04
|
||||
end_time: 2026-08-10
|
||||
account: 1000000
|
||||
benchmark: SPY
|
||||
exchange_kwargs:
|
||||
codes: "{{ UNIVERSE }}"
|
||||
deal_price: $close
|
||||
freq: day
|
||||
open_cost: 0.0005
|
||||
close_cost: 0.0015
|
||||
min_cost: 5.0
|
||||
risk_analysis_freq: 1d
|
||||
@@ -0,0 +1,106 @@
|
||||
# QUEUE-13 — Weekly rebalance reproduction on a second OOS window.
|
||||
# Q07 (exp 39) proved weekly recompute on test 2026-01-04..2026-08-10 (net +12.51%,
|
||||
# IR 1.24) but that is a single OOS window. Before promoting the weekly construction
|
||||
# to a live round, reproduce it on a disjoint window: test 2025-01-02..2025-12-31
|
||||
# with train/valid shifted to end 2024.
|
||||
# Change vs exp-26 reference: segments shifted only (train ends 2024-08, test = 2025);
|
||||
# strategy is the SAME weekly recompute as exp 39. Label stays 5d.
|
||||
# Acceptance: net_IR > 0.21 AND net_ann > +2.13% on the 2025 window.
|
||||
# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q13_weekly_second_window.yaml \
|
||||
# experiment_name=tac-rd-q13-weekly-second-window
|
||||
{%- set LAKE = TAC_LAKE_DIR %}
|
||||
{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
|
||||
{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
|
||||
|
||||
qlib_init:
|
||||
provider_uri: "{{ LAKE }}"
|
||||
region: us
|
||||
expression_cache: null
|
||||
dataset_cache: null
|
||||
calendar_provider:
|
||||
class: tac_qlib.data.providers.LakeCalendarProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||
instrument_provider:
|
||||
class: tac_qlib.data.providers.LakeInstrumentProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
||||
feature_provider:
|
||||
class: tac_qlib.data.providers.LakeFeatureProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||
exp_manager:
|
||||
class: MLflowExpManager
|
||||
module_path: qlib.workflow.expm
|
||||
kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q13-weekly-second-window" }
|
||||
|
||||
task:
|
||||
model:
|
||||
class: RankICEnsembleLGBModel
|
||||
module_path: tac_qlib.contrib.model.rank_ensemble
|
||||
kwargs:
|
||||
loss: mse
|
||||
learning_rate: 0.02
|
||||
num_leaves: 31
|
||||
n_estimators: 3000
|
||||
num_boost_round: 3000
|
||||
early_stopping_rounds: 200
|
||||
min_data_in_leaf: 20
|
||||
lambda_l2: 0.5
|
||||
colsample_bytree: 0.8
|
||||
subsample: 0.8
|
||||
subsample_freq: 1
|
||||
reg_alpha: 0.1
|
||||
reg_lambda: 1.0
|
||||
seeds: "42,7,2026,99,123"
|
||||
|
||||
dataset:
|
||||
class: DatasetH
|
||||
module_path: qlib.data.dataset
|
||||
kwargs:
|
||||
handler:
|
||||
class: TACHandler
|
||||
module_path: tac_qlib.contrib.data.handler
|
||||
kwargs:
|
||||
instruments: "{{ UNIVERSE }}"
|
||||
start_time: 2015-01-03
|
||||
end_time: 2025-12-31
|
||||
fit_start_time: 2016-01-04
|
||||
fit_end_time: 2024-08-30
|
||||
freq: day
|
||||
lake_root: "{{ LAKE }}"
|
||||
market: US
|
||||
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||
feature_fields: "{{ FEATURES }}"
|
||||
infer_processors:
|
||||
- { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2024-08-30" } }
|
||||
- { class: ProcessInf, kwargs: {} }
|
||||
- { class: CSRankNorm, kwargs: {} }
|
||||
- { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2024-08-30" } }
|
||||
- { class: Fillna, kwargs: {} }
|
||||
segments:
|
||||
train: [2016-01-04, 2024-08-30]
|
||||
valid: [2024-09-03, 2024-12-31]
|
||||
test: [2025-01-02, 2025-12-31]
|
||||
|
||||
record:
|
||||
- { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
|
||||
- { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
|
||||
- class: PortAnaRecord
|
||||
module_path: qlib.workflow.record_temp
|
||||
kwargs:
|
||||
config:
|
||||
strategy:
|
||||
class: WeeklyRebalanceDropoutStrategy
|
||||
module_path: tac_qlib.contrib.strategy.weekly_rebalance
|
||||
kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
|
||||
backtest:
|
||||
start_time: 2025-01-02
|
||||
end_time: 2025-12-31
|
||||
account: 1000000
|
||||
benchmark: SPY
|
||||
exchange_kwargs:
|
||||
codes: "{{ UNIVERSE }}"
|
||||
deal_price: $close
|
||||
freq: day
|
||||
open_cost: 0.0005
|
||||
close_cost: 0.0015
|
||||
min_cost: 5.0
|
||||
risk_analysis_freq: 1d
|
||||
@@ -0,0 +1,107 @@
|
||||
# QUEUE-14 — Out-of-universe validation: compact stochastic set on single-stock names.
|
||||
# The 50-ETF panel results (compact feature set, RankIC 0.0663) are panel-specific;
|
||||
# book/CLAIMS.md marks "generalizes to other universes" HYPOTHESIS - TODO(evidence-needed).
|
||||
# Change vs exp-26 reference: universe -> 30 liquid US single-stock names.
|
||||
# PREREQUISITE: backfill lake bars + sp/ta features for these symbols (full range,
|
||||
# explicit start/end) — the stock panel currently has only ~180d of data (2025-12-01+).
|
||||
# Backfill: get_lake_bars symbols=... start=2000-01-03 then
|
||||
# get_lake_sp symbol=<s> start=2000-01-03 end=<today> fit_end=<train-end> persist=true
|
||||
# Acceptance: RankIC > 0.03, ICIR > 0.15, net IR > 0 on the stock universe.
|
||||
# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q14_out_of_universe.yaml \
|
||||
# experiment_name=tac-rd-q14-out-of-universe
|
||||
{%- set LAKE = TAC_LAKE_DIR %}
|
||||
{%- set UNIVERSE = "AAPL,MSFT,NVDA,AMZN,GOOGL,META,TSLA,AVGO,AMD,JPM,UNH,PG,JNJ,MA,V,WMT,DIS,HD,KO,PEP,BAC,XOM,MCD,ABBV,COST,CRM,NFLX,ORCL,IBM,T" %}
|
||||
{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
|
||||
|
||||
qlib_init:
|
||||
provider_uri: "{{ LAKE }}"
|
||||
region: us
|
||||
expression_cache: null
|
||||
dataset_cache: null
|
||||
calendar_provider:
|
||||
class: tac_qlib.data.providers.LakeCalendarProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||
instrument_provider:
|
||||
class: tac_qlib.data.providers.LakeInstrumentProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
||||
feature_provider:
|
||||
class: tac_qlib.data.providers.LakeFeatureProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||
exp_manager:
|
||||
class: MLflowExpManager
|
||||
module_path: qlib.workflow.expm
|
||||
kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q14-out-of-universe" }
|
||||
|
||||
task:
|
||||
model:
|
||||
class: RankICEnsembleLGBModel
|
||||
module_path: tac_qlib.contrib.model.rank_ensemble
|
||||
kwargs:
|
||||
loss: mse
|
||||
learning_rate: 0.02
|
||||
num_leaves: 31
|
||||
n_estimators: 3000
|
||||
num_boost_round: 3000
|
||||
early_stopping_rounds: 200
|
||||
min_data_in_leaf: 20
|
||||
lambda_l2: 0.5
|
||||
colsample_bytree: 0.8
|
||||
subsample: 0.8
|
||||
subsample_freq: 1
|
||||
reg_alpha: 0.1
|
||||
reg_lambda: 1.0
|
||||
seeds: "42,7,2026,99,123"
|
||||
|
||||
dataset:
|
||||
class: DatasetH
|
||||
module_path: qlib.data.dataset
|
||||
kwargs:
|
||||
handler:
|
||||
class: TACHandler
|
||||
module_path: tac_qlib.contrib.data.handler
|
||||
kwargs:
|
||||
instruments: "{{ UNIVERSE }}"
|
||||
start_time: 2015-01-03
|
||||
end_time: 2026-08-10
|
||||
fit_start_time: 2016-01-04
|
||||
fit_end_time: 2025-09-01
|
||||
freq: day
|
||||
lake_root: "{{ LAKE }}"
|
||||
market: US
|
||||
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||
feature_fields: "{{ FEATURES }}"
|
||||
infer_processors:
|
||||
- { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
||||
- { class: ProcessInf, kwargs: {} }
|
||||
- { class: CSRankNorm, kwargs: {} }
|
||||
- { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
||||
- { class: Fillna, kwargs: {} }
|
||||
segments:
|
||||
train: [2016-01-04, 2025-09-01]
|
||||
valid: [2025-09-03, 2026-01-03]
|
||||
test: [2026-01-04, 2026-08-10]
|
||||
|
||||
record:
|
||||
- { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
|
||||
- { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
|
||||
- class: PortAnaRecord
|
||||
module_path: qlib.workflow.record_temp
|
||||
kwargs:
|
||||
config:
|
||||
strategy:
|
||||
class: TopkDropoutStrategy
|
||||
module_path: qlib.contrib.strategy
|
||||
kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
|
||||
backtest:
|
||||
start_time: 2026-01-04
|
||||
end_time: 2026-08-10
|
||||
account: 1000000
|
||||
benchmark: SPY
|
||||
exchange_kwargs:
|
||||
codes: "{{ UNIVERSE }}"
|
||||
deal_price: $close
|
||||
freq: day
|
||||
open_cost: 0.0005
|
||||
close_cost: 0.0015
|
||||
min_cost: 5.0
|
||||
risk_analysis_freq: 1d
|
||||
@@ -0,0 +1,104 @@
|
||||
# QUEUE-15 — 5-seed vs single-model clean A/B on the compact stochastic set.
|
||||
# CLAIMS.md HYPOTHESIS: "5-seed RankIC ensemble raises performance vs single model
|
||||
# on ablated set" — pre-clean-lake exp 12 idea, re-validated directionally by exp
|
||||
# 22–24, never a clean A/B post-reset. Seed count is load-bearing (exp 28: 2<5).
|
||||
# Change vs exp-26 reference: seeds "42,7,2026,99,123" -> single seed "2026".
|
||||
# Acceptance: single-model RankIC < 0.0663, net_IR < 0.21 (ensemble beats single).
|
||||
# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q15_single_seed.yaml \
|
||||
# experiment_name=tac-rd-q15-single-seed
|
||||
{%- set LAKE = TAC_LAKE_DIR %}
|
||||
{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
|
||||
{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
|
||||
|
||||
qlib_init:
|
||||
provider_uri: "{{ LAKE }}"
|
||||
region: us
|
||||
expression_cache: null
|
||||
dataset_cache: null
|
||||
calendar_provider:
|
||||
class: tac_qlib.data.providers.LakeCalendarProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||
instrument_provider:
|
||||
class: tac_qlib.data.providers.LakeInstrumentProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
||||
feature_provider:
|
||||
class: tac_qlib.data.providers.LakeFeatureProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||
exp_manager:
|
||||
class: MLflowExpManager
|
||||
module_path: qlib.workflow.expm
|
||||
kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q15-single-seed" }
|
||||
|
||||
task:
|
||||
model:
|
||||
class: RankICEnsembleLGBModel
|
||||
module_path: tac_qlib.contrib.model.rank_ensemble
|
||||
kwargs:
|
||||
loss: mse
|
||||
learning_rate: 0.02
|
||||
num_leaves: 31
|
||||
n_estimators: 3000
|
||||
num_boost_round: 3000
|
||||
early_stopping_rounds: 200
|
||||
min_data_in_leaf: 20
|
||||
lambda_l2: 0.5
|
||||
colsample_bytree: 0.8
|
||||
subsample: 0.8
|
||||
subsample_freq: 1
|
||||
reg_alpha: 0.1
|
||||
reg_lambda: 1.0
|
||||
seeds: "2026"
|
||||
|
||||
dataset:
|
||||
class: DatasetH
|
||||
module_path: qlib.data.dataset
|
||||
kwargs:
|
||||
handler:
|
||||
class: TACHandler
|
||||
module_path: tac_qlib.contrib.data.handler
|
||||
kwargs:
|
||||
instruments: "{{ UNIVERSE }}"
|
||||
start_time: 2015-01-03
|
||||
end_time: 2026-08-10
|
||||
fit_start_time: 2016-01-04
|
||||
fit_end_time: 2025-09-01
|
||||
freq: day
|
||||
lake_root: "{{ LAKE }}"
|
||||
market: US
|
||||
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||
feature_fields: "{{ FEATURES }}"
|
||||
infer_processors:
|
||||
- { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
||||
- { class: ProcessInf, kwargs: {} }
|
||||
- { class: CSRankNorm, kwargs: {} }
|
||||
- { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
||||
- { class: Fillna, kwargs: {} }
|
||||
segments:
|
||||
train: [2016-01-04, 2025-09-01]
|
||||
valid: [2025-09-03, 2026-01-03]
|
||||
test: [2026-01-04, 2026-08-10]
|
||||
|
||||
record:
|
||||
- { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
|
||||
- { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
|
||||
- class: PortAnaRecord
|
||||
module_path: qlib.workflow.record_temp
|
||||
kwargs:
|
||||
config:
|
||||
strategy:
|
||||
class: TopkDropoutStrategy
|
||||
module_path: qlib.contrib.strategy
|
||||
kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
|
||||
backtest:
|
||||
start_time: 2026-01-04
|
||||
end_time: 2026-08-10
|
||||
account: 1000000
|
||||
benchmark: SPY
|
||||
exchange_kwargs:
|
||||
codes: "{{ UNIVERSE }}"
|
||||
deal_price: $close
|
||||
freq: day
|
||||
open_cost: 0.0005
|
||||
close_cost: 0.0015
|
||||
min_cost: 5.0
|
||||
risk_analysis_freq: 1d
|
||||
@@ -0,0 +1,105 @@
|
||||
# QUEUE-16 — HMM family added as model features to the compact set.
|
||||
# CLAIMS.md HYPOTHESIS: "Dropping model-specific feature families (ou, hmm)
|
||||
# improves the rank signal" — exp 25 cleanly tested OU (adding it hurts: IC 0.0511->0.0343);
|
||||
# hmm-as-features has NOT been clean A/B'd post-reset (exp 42 tested hmm as an entry
|
||||
# GATE overlay, refuted). This run adds the hmm family columns to the compact set.
|
||||
# Change vs exp-26 reference: features += sp_hmm_p_regime1, sp_hmm_state.
|
||||
# Acceptance (prune-hypothesis): no improvement — RankIC <= 0.0663, net_IR <= 0.21.
|
||||
# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q16_hmm_features.yaml \
|
||||
# experiment_name=tac-rd-q16-hmm-features
|
||||
{%- set LAKE = TAC_LAKE_DIR %}
|
||||
{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
|
||||
{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sp_hmm_p_regime1,sp_hmm_state" %}
|
||||
|
||||
qlib_init:
|
||||
provider_uri: "{{ LAKE }}"
|
||||
region: us
|
||||
expression_cache: null
|
||||
dataset_cache: null
|
||||
calendar_provider:
|
||||
class: tac_qlib.data.providers.LakeCalendarProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||
instrument_provider:
|
||||
class: tac_qlib.data.providers.LakeInstrumentProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
||||
feature_provider:
|
||||
class: tac_qlib.data.providers.LakeFeatureProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||
exp_manager:
|
||||
class: MLflowExpManager
|
||||
module_path: qlib.workflow.expm
|
||||
kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q16-hmm-features" }
|
||||
|
||||
task:
|
||||
model:
|
||||
class: RankICEnsembleLGBModel
|
||||
module_path: tac_qlib.contrib.model.rank_ensemble
|
||||
kwargs:
|
||||
loss: mse
|
||||
learning_rate: 0.02
|
||||
num_leaves: 31
|
||||
n_estimators: 3000
|
||||
num_boost_round: 3000
|
||||
early_stopping_rounds: 200
|
||||
min_data_in_leaf: 20
|
||||
lambda_l2: 0.5
|
||||
colsample_bytree: 0.8
|
||||
subsample: 0.8
|
||||
subsample_freq: 1
|
||||
reg_alpha: 0.1
|
||||
reg_lambda: 1.0
|
||||
seeds: "42,7,2026,99,123"
|
||||
|
||||
dataset:
|
||||
class: DatasetH
|
||||
module_path: qlib.data.dataset
|
||||
kwargs:
|
||||
handler:
|
||||
class: TACHandler
|
||||
module_path: tac_qlib.contrib.data.handler
|
||||
kwargs:
|
||||
instruments: "{{ UNIVERSE }}"
|
||||
start_time: 2015-01-03
|
||||
end_time: 2026-08-10
|
||||
fit_start_time: 2016-01-04
|
||||
fit_end_time: 2025-09-01
|
||||
freq: day
|
||||
lake_root: "{{ LAKE }}"
|
||||
market: US
|
||||
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||
feature_fields: "{{ FEATURES }}"
|
||||
infer_processors:
|
||||
- { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
||||
- { class: ProcessInf, kwargs: {} }
|
||||
- { class: CSRankNorm, kwargs: {} }
|
||||
- { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
||||
- { class: Fillna, kwargs: {} }
|
||||
segments:
|
||||
train: [2016-01-04, 2025-09-01]
|
||||
valid: [2025-09-03, 2026-01-03]
|
||||
test: [2026-01-04, 2026-08-10]
|
||||
|
||||
record:
|
||||
- { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
|
||||
- { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
|
||||
- class: PortAnaRecord
|
||||
module_path: qlib.workflow.record_temp
|
||||
kwargs:
|
||||
config:
|
||||
strategy:
|
||||
class: TopkDropoutStrategy
|
||||
module_path: qlib.contrib.strategy
|
||||
kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
|
||||
backtest:
|
||||
start_time: 2026-01-04
|
||||
end_time: 2026-08-10
|
||||
account: 1000000
|
||||
benchmark: SPY
|
||||
exchange_kwargs:
|
||||
codes: "{{ UNIVERSE }}"
|
||||
deal_price: $close
|
||||
freq: day
|
||||
open_cost: 0.0005
|
||||
close_cost: 0.0015
|
||||
min_cost: 5.0
|
||||
risk_analysis_freq: 1d
|
||||
@@ -0,0 +1,105 @@
|
||||
# QUEUE-17 — Realized-moments family added to the compact set.
|
||||
# CLAIMS.md HYPOTHESIS: "Adding moment/volatility families regresses the signal"
|
||||
# (idea: pre-clean-lake exp 11). M1 momentum bundle (exp 29) and M3 GARCH (exp 31)
|
||||
# were refuted post-reset; the realized-moments family (sp_rskew/sp_rkurt/sp_dsv)
|
||||
# has NOT been clean A/B'd. This run adds the moments columns to the compact set.
|
||||
# Change vs exp-26 reference: features += sp_rskew_5,sp_rskew_22,sp_rkurt_5,sp_rkurt_22,sp_dsv_5,sp_dsv_22.
|
||||
# Acceptance (prune-hypothesis): no improvement — RankIC <= 0.0663, net_IR <= 0.21.
|
||||
# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q17_moments_features.yaml \
|
||||
# experiment_name=tac-rd-q17-moments-features
|
||||
{%- set LAKE = TAC_LAKE_DIR %}
|
||||
{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
|
||||
{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sp_rskew_5,sp_rskew_22,sp_rkurt_5,sp_rkurt_22,sp_dsv_5,sp_dsv_22" %}
|
||||
|
||||
qlib_init:
|
||||
provider_uri: "{{ LAKE }}"
|
||||
region: us
|
||||
expression_cache: null
|
||||
dataset_cache: null
|
||||
calendar_provider:
|
||||
class: tac_qlib.data.providers.LakeCalendarProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||
instrument_provider:
|
||||
class: tac_qlib.data.providers.LakeInstrumentProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
||||
feature_provider:
|
||||
class: tac_qlib.data.providers.LakeFeatureProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||
exp_manager:
|
||||
class: MLflowExpManager
|
||||
module_path: qlib.workflow.expm
|
||||
kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q17-moments-features" }
|
||||
|
||||
task:
|
||||
model:
|
||||
class: RankICEnsembleLGBModel
|
||||
module_path: tac_qlib.contrib.model.rank_ensemble
|
||||
kwargs:
|
||||
loss: mse
|
||||
learning_rate: 0.02
|
||||
num_leaves: 31
|
||||
n_estimators: 3000
|
||||
num_boost_round: 3000
|
||||
early_stopping_rounds: 200
|
||||
min_data_in_leaf: 20
|
||||
lambda_l2: 0.5
|
||||
colsample_bytree: 0.8
|
||||
subsample: 0.8
|
||||
subsample_freq: 1
|
||||
reg_alpha: 0.1
|
||||
reg_lambda: 1.0
|
||||
seeds: "42,7,2026,99,123"
|
||||
|
||||
dataset:
|
||||
class: DatasetH
|
||||
module_path: qlib.data.dataset
|
||||
kwargs:
|
||||
handler:
|
||||
class: TACHandler
|
||||
module_path: tac_qlib.contrib.data.handler
|
||||
kwargs:
|
||||
instruments: "{{ UNIVERSE }}"
|
||||
start_time: 2015-01-03
|
||||
end_time: 2026-08-10
|
||||
fit_start_time: 2016-01-04
|
||||
fit_end_time: 2025-09-01
|
||||
freq: day
|
||||
lake_root: "{{ LAKE }}"
|
||||
market: US
|
||||
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||
feature_fields: "{{ FEATURES }}"
|
||||
infer_processors:
|
||||
- { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
||||
- { class: ProcessInf, kwargs: {} }
|
||||
- { class: CSRankNorm, kwargs: {} }
|
||||
- { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
||||
- { class: Fillna, kwargs: {} }
|
||||
segments:
|
||||
train: [2016-01-04, 2025-09-01]
|
||||
valid: [2025-09-03, 2026-01-03]
|
||||
test: [2026-01-04, 2026-08-10]
|
||||
|
||||
record:
|
||||
- { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
|
||||
- { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
|
||||
- class: PortAnaRecord
|
||||
module_path: qlib.workflow.record_temp
|
||||
kwargs:
|
||||
config:
|
||||
strategy:
|
||||
class: TopkDropoutStrategy
|
||||
module_path: qlib.contrib.strategy
|
||||
kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
|
||||
backtest:
|
||||
start_time: 2026-01-04
|
||||
end_time: 2026-08-10
|
||||
account: 1000000
|
||||
benchmark: SPY
|
||||
exchange_kwargs:
|
||||
codes: "{{ UNIVERSE }}"
|
||||
deal_price: $close
|
||||
freq: day
|
||||
open_cost: 0.0005
|
||||
close_cost: 0.0015
|
||||
min_cost: 5.0
|
||||
risk_analysis_freq: 1d
|
||||
@@ -0,0 +1,106 @@
|
||||
# QUEUE-18 — OptimalStopControl clean re-test vs TopkDropout (exp 13/14 claim).
|
||||
# CLAIMS.md HYPOTHESIS: "TopkDropout beats stochastic-control OptimalStopControl on
|
||||
# the ensemble signal" — exp 13/14 were pre-clean-lake; never re-tested post-reset.
|
||||
# Same compact signal as the exp-26 reference; ONLY the strategy changes to
|
||||
# OptimalStopControl with exp-13 params (entry 0.85 / exit 0.7 / hold 10 / sl -0.08).
|
||||
# PREREQUISITE: tac_qlib/contrib/strategy/optimal_stop.py must be synced to the venv
|
||||
# site-packages snapshot before running (see /app/AGENTS.md).
|
||||
# Acceptance: TopkDropout net_IR >= stop-control net_IR; document cost drag of both.
|
||||
# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q18_optstop.yaml \
|
||||
# experiment_name=tac-rd-q18-optstop
|
||||
{%- set LAKE = TAC_LAKE_DIR %}
|
||||
{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
|
||||
{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
|
||||
|
||||
qlib_init:
|
||||
provider_uri: "{{ LAKE }}"
|
||||
region: us
|
||||
expression_cache: null
|
||||
dataset_cache: null
|
||||
calendar_provider:
|
||||
class: tac_qlib.data.providers.LakeCalendarProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||
instrument_provider:
|
||||
class: tac_qlib.data.providers.LakeInstrumentProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
||||
feature_provider:
|
||||
class: tac_qlib.data.providers.LakeFeatureProvider
|
||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||
exp_manager:
|
||||
class: MLflowExpManager
|
||||
module_path: qlib.workflow.expm
|
||||
kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q18-optstop" }
|
||||
|
||||
task:
|
||||
model:
|
||||
class: RankICEnsembleLGBModel
|
||||
module_path: tac_qlib.contrib.model.rank_ensemble
|
||||
kwargs:
|
||||
loss: mse
|
||||
learning_rate: 0.02
|
||||
num_leaves: 31
|
||||
n_estimators: 3000
|
||||
num_boost_round: 3000
|
||||
early_stopping_rounds: 200
|
||||
min_data_in_leaf: 20
|
||||
lambda_l2: 0.5
|
||||
colsample_bytree: 0.8
|
||||
subsample: 0.8
|
||||
subsample_freq: 1
|
||||
reg_alpha: 0.1
|
||||
reg_lambda: 1.0
|
||||
seeds: "42,7,2026,99,123"
|
||||
|
||||
dataset:
|
||||
class: DatasetH
|
||||
module_path: qlib.data.dataset
|
||||
kwargs:
|
||||
handler:
|
||||
class: TACHandler
|
||||
module_path: tac_qlib.contrib.data.handler
|
||||
kwargs:
|
||||
instruments: "{{ UNIVERSE }}"
|
||||
start_time: 2015-01-03
|
||||
end_time: 2026-08-10
|
||||
fit_start_time: 2016-01-04
|
||||
fit_end_time: 2025-09-01
|
||||
freq: day
|
||||
lake_root: "{{ LAKE }}"
|
||||
market: US
|
||||
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||
feature_fields: "{{ FEATURES }}"
|
||||
infer_processors:
|
||||
- { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
||||
- { class: ProcessInf, kwargs: {} }
|
||||
- { class: CSRankNorm, kwargs: {} }
|
||||
- { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
||||
- { class: Fillna, kwargs: {} }
|
||||
segments:
|
||||
train: [2016-01-04, 2025-09-01]
|
||||
valid: [2025-09-03, 2026-01-03]
|
||||
test: [2026-01-04, 2026-08-10]
|
||||
|
||||
record:
|
||||
- { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
|
||||
- { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
|
||||
- class: PortAnaRecord
|
||||
module_path: qlib.workflow.record_temp
|
||||
kwargs:
|
||||
config:
|
||||
strategy:
|
||||
class: OptimalStopControl
|
||||
module_path: tac_qlib.contrib.strategy.optimal_stop
|
||||
kwargs: { signal: "<PRED>", topk: 10, entry_pct: 0.85, exit_pct: 0.7, max_hold_days: 10, min_hold_days: 2, sl: -0.08 }
|
||||
backtest:
|
||||
start_time: 2026-01-04
|
||||
end_time: 2026-08-10
|
||||
account: 1000000
|
||||
benchmark: SPY
|
||||
exchange_kwargs:
|
||||
codes: "{{ UNIVERSE }}"
|
||||
deal_price: $close
|
||||
freq: day
|
||||
open_cost: 0.0005
|
||||
close_cost: 0.0015
|
||||
min_cost: 5.0
|
||||
risk_analysis_freq: 1d
|
||||
Reference in New Issue
Block a user