Add csi500 benchmark for MLP model. (#1215)

* Add csi500 benchmark for MLP model.

* Update MLP metric for Alpha158 dataset.

Co-authored-by: vincilee <vincilee1994@outlook.com>
Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>

examples/benchmarks/MLP/workflow_config_mlp_Alpha158_csi500.yaml

@@ -0,0 +1,102 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi500
+benchmark: &benchmark SH000905
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+    infer_processors: [
+        {
+            "class" : "DropCol", 
+            "kwargs":{"col_list": ["VWAP0"]}
+        },
+        {
+             "class" : "CSZFillna", 
+             "kwargs":{"fields_group": "feature"}
+        }
+    ]
+    learn_processors: [
+        {
+            "class" : "DropCol", 
+            "kwargs":{"col_list": ["VWAP0"]}
+        },
+        {
+            "class" : "DropnaProcessor", 
+            "kwargs":{"fields_group": "feature"}
+        },
+        "DropnaLabel",
+        {
+            "class": "CSZScoreNorm", 
+            "kwargs": {"fields_group": "label"}
+        }
+    ]
+    process_type: "independent"
+
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy
+        kwargs:
+            signal:
+                - <MODEL> 
+                - <DATASET>
+            topk: 50
+            n_drop: 5
+    backtest:
+        start_time: 2017-01-01
+        end_time: 2020-08-01
+        account: 100000000
+        benchmark: *benchmark
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
+task:
+    model:
+        class: DNNModelPytorch
+        module_path: qlib.contrib.model.pytorch_nn
+        kwargs:
+            loss: mse
+            lr: 0.002
+            lr_decay: 0.96
+            lr_decay_steps: 100
+            optimizer: adam
+            max_steps: 8000
+            batch_size: 8192
+            GPU: 0
+            weight_decay: 0.0002
+            pt_model_kwargs:
+              input_dim: 157
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: Alpha158
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            ana_long_short: False
+            ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            config: *port_analysis_config

examples/benchmarks/MLP/workflow_config_mlp_Alpha360_csi500.yaml

@@ -0,0 +1,89 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi500
+benchmark: &benchmark SH000905
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+    infer_processors:
+        - class: RobustZScoreNorm
+          kwargs:
+              fields_group: feature
+              clip_outlier: true
+        - class: Fillna
+          kwargs:
+              fields_group: feature
+    learn_processors:
+        - class: DropnaLabel
+        - class: CSRankNorm
+          kwargs:
+              fields_group: label
+    label: ["Ref($close, -2) / Ref($close, -1) - 1"]
+
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy
+        kwargs:
+            signal:
+                - <MODEL> 
+                - <DATASET>
+            topk: 50
+            n_drop: 5
+    backtest:
+        start_time: 2017-01-01
+        end_time: 2020-08-01
+        account: 100000000
+        benchmark: *benchmark
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
+task:
+    model:
+        class: DNNModelPytorch
+        module_path: qlib.contrib.model.pytorch_nn
+        kwargs:
+            loss: mse
+            lr: 0.002
+            lr_decay: 0.96
+            lr_decay_steps: 100
+            optimizer: adam
+            max_steps: 8000
+            batch_size: 4096
+            GPU: 0
+            pt_model_kwargs:
+              input_dim: 360
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: Alpha360
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            ana_long_short: False
+            ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            config: *port_analysis_config

examples/benchmarks/README.md

@@ -110,6 +110,7 @@ python run_all_model.py run 3 lightgbm Alpha158 csi500  # for models with random
 | Model Name | Dataset  | IC          | ICIR        | Rank IC     | Rank ICIR   | Annualized Return | Information Ratio | Max Drawdown |
 |------------|----------|-------------|-------------|-------------|-------------|-------------------|-------------------|--------------|
 | Linear     | Alpha158 | 0.0332±0.00 | 0.3044±0.00 | 0.0462±0.00 | 0.4326±0.00 | 0.0382±0.00       | 0.1723±0.00       | -0.4876±0.00 |
+| MLP        | Alpha158 | 0.0229±0.01 | 0.2181±0.05 | 0.0360±0.00 | 0.3409±0.02 | 0.0043±0.02       | 0.0602±0.27       | -0.2184±0.04 |
 | LightGBM   | Alpha158 | 0.0399±0.00 | 0.4065±0.00 | 0.0482±0.00 | 0.5101±0.00 | 0.1284±0.00       | 1.5650±0.00       | -0.0635±0.00 |
 | CatBoost   | Alpha158 | 0.0345±0.00 | 0.2855±0.00 | 0.0417±0.00 | 0.3740±0.00 | 0.0496±0.00       | 0.5977±0.00       | -0.1496±0.00 |
 | DoubleEnsemble  | Alpha158 | 0.0380±0.00 | 0.3659±0.00 | 0.0442±0.00 | 0.4324±0.00 | 0.0382±0.00       | 0.1723±0.00       | -0.4876±0.00 |
@@ -117,6 +118,7 @@ python run_all_model.py run 3 lightgbm Alpha158 csi500  # for models with random
 ### Alpha360 dataset
 | Model Name | Dataset  | IC          | ICIR        | Rank IC     | Rank ICIR   | Annualized Return | Information Ratio | Max Drawdown |
 |------------|----------|-------------|-------------|-------------|-------------|-------------------|-------------------|--------------|
+| MLP        | Alpha360 | 0.0258±0.00 | 0.2021±0.02 | 0.0426±0.00 | 0.3840±0.02 | 0.0022±0.02       | 0.0301±0.26       | -0.2064±0.02 |
 | LightGBM   | Alpha360 | 0.0400±0.00 | 0.3605±0.00 | 0.0536±0.00 | 0.5431±0.00 | 0.0505±0.00       | 0.7658±0.02       | -0.1880±0.00 |
 | CatBoost   | Alpha360 | 0.0382±0.00 | 0.3229±0.00 | 0.0489±0.00 | 0.4649±0.00 | 0.0297±0.00       | 0.4227±0.02       | -0.1499±0.01 |
 | DoubleEnsemble  | Alpha360 | 0.0361±0.00 | 0.3092±0.00 | 0.0499±0.00 | 0.4793±0.00 | 0.0382±0.00       | 0.1723±0.02       | -0.4876±0.00 |