130 lines
4.5 KiB
YAML
130 lines
4.5 KiB
YAML
# -----------------------------------------------------------------------------
|
|
# Tune run 1: wider, longer-horizon, de-duplicated universe.
|
|
#
|
|
# Baseline (exp 1 / run f29f5446): IC 0.071 / ICIR 0.17, Rank IC ~0.014;
|
|
# strategy +4.9% ann (raw) vs benchmark ~+89% ann; excess return w/ cost
|
|
# -0.94 ann, IR -2.23, excess max drawdown -18.9%. topk=2 with 24 trades over
|
|
# 27 days on a universe of correlated ETFs + leveraged hedges (VXX/USO/SLV)
|
|
# produced high turnover and a portfolio that trailed AAPL badly.
|
|
#
|
|
# Changes:
|
|
# - universe: drop leveraged/noisy names (VXX, USO, SLV, BIL) and near-
|
|
# duplicate index baskets (GPIQ, QQQE, KTEC); keep 10 liquid core names.
|
|
# - label: 5-day forward return (Ref($close,-6)/Ref($close,-1)-1) to cut
|
|
# single-day noise and match the intended holding horizon.
|
|
# - topk 2 -> 5, n_drop 1: more diversification, lower turnover per name.
|
|
# - benchmark AAPL -> QQQ (a real index ETF the universe tracks).
|
|
# - model: learning_rate 0.03, 300 estimators (slower, deeper fit).
|
|
#
|
|
# Trigger:
|
|
# rd_run_workflow config_path=tac-qlib/workflows/tune_run1_wider_5d.yaml \
|
|
# experiment_name=tac-rd-tune
|
|
# -----------------------------------------------------------------------------
|
|
{%- set LAKE = TAC_LAKE_DIR %}
|
|
|
|
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-tune"
|
|
|
|
task:
|
|
model:
|
|
class: LGBModel
|
|
module_path: qlib.contrib.model.gbdt
|
|
kwargs:
|
|
loss: mse
|
|
learning_rate: 0.03
|
|
num_leaves: 15
|
|
n_estimators: 300
|
|
colsample_bytree: 0.8
|
|
subsample: 0.8
|
|
subsample_freq: 1
|
|
reg_alpha: 0.01
|
|
reg_lambda: 0.01
|
|
seed: 2026
|
|
|
|
dataset:
|
|
class: DatasetH
|
|
module_path: qlib.data.dataset
|
|
kwargs:
|
|
handler:
|
|
class: TACHandler
|
|
module_path: tac_qlib.contrib.data.handler
|
|
kwargs:
|
|
instruments: AAPL,MSFT,TSLA,QQQ,IVV,SMH,TLT,IBIT,MCHI,AIQ
|
|
start_time: 2000-01-03
|
|
end_time: 2026-08-06
|
|
fit_start_time: 2026-03-01
|
|
fit_end_time: 2026-05-31
|
|
freq: day
|
|
lake_root: "{{ LAKE }}"
|
|
market: US
|
|
label: "Ref($close,-6)/Ref($close,-1)-1"
|
|
segments:
|
|
train: [2026-03-01, 2026-05-31]
|
|
valid: [2026-06-01, 2026-06-30]
|
|
test: [2026-07-01, 2026-08-06]
|
|
|
|
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: 5
|
|
n_drop: 1
|
|
only_tradable: true
|
|
risk_degree: 0.95
|
|
backtest:
|
|
start_time: 2026-07-01
|
|
end_time: 2026-08-06
|
|
account: 1000000
|
|
benchmark: QQQ
|
|
exchange_kwargs:
|
|
codes: AAPL,MSFT,TSLA,QQQ,IVV,SMH,TLT,IBIT,MCHI,AIQ
|
|
deal_price: $close
|
|
freq: day
|
|
open_cost: 0.0005
|
|
close_cost: 0.0015
|
|
min_cost: 5.0
|
|
risk_analysis_freq: 1d
|