diff --git a/rdagent/scenarios/kaggle/docker/Dockerfile b/rdagent/scenarios/kaggle/docker/Dockerfile
index 26d3bc3c..50f2aa07 100644
--- a/rdagent/scenarios/kaggle/docker/Dockerfile
+++ b/rdagent/scenarios/kaggle/docker/Dockerfile
@@ -24,3 +24,5 @@ RUN pip install catboost
 RUN pip install xgboost
 RUN pip install sparse
 RUN pip install lightgbm 
+RUN pip install pyarrow
+RUN pip install fastparquet
\ No newline at end of file
diff --git a/rdagent/scenarios/kaggle/experiment/meta_tpl/model/model_xgboost.py b/rdagent/scenarios/kaggle/experiment/meta_tpl/model/model_xgboost.py
index 64784224..43ecd310 100644
--- a/rdagent/scenarios/kaggle/experiment/meta_tpl/model/model_xgboost.py
+++ b/rdagent/scenarios/kaggle/experiment/meta_tpl/model/model_xgboost.py
@@ -18,9 +18,10 @@ def fit(X_train: pd.DataFrame, y_train: pd.DataFrame, X_valid: pd.DataFrame, y_v
     dtrain = xgb.DMatrix(X_train, label=y_train)
     dvalid = xgb.DMatrix(X_valid, label=y_valid)
 
-    # TODO: for quick running....
+    # Parameters for regression
     params = {
-        "nthred": -1,
+        "objective": "reg:squarederror",  # Use squared error for regression
+        "nthread": -1,
     }
     num_round = 100
 
diff --git a/rdagent/scenarios/kaggle/experiment/optiver-realized-volatility-prediction_template/fea_share_preprocess.py b/rdagent/scenarios/kaggle/experiment/optiver-realized-volatility-prediction_template/fea_share_preprocess.py
index 54c3c8a7..2368dff5 100644
--- a/rdagent/scenarios/kaggle/experiment/optiver-realized-volatility-prediction_template/fea_share_preprocess.py
+++ b/rdagent/scenarios/kaggle/experiment/optiver-realized-volatility-prediction_template/fea_share_preprocess.py
@@ -11,16 +11,18 @@ from sklearn.preprocessing import OrdinalEncoder
 
 def prepreprocess():
     # Load the training data
-    train_df = pd.read_csv("/kaggle/input/optiver-realized-volatility-prediction/train.csv")
+    train_df = pd.read_csv("/kaggle/input/train.csv").head(1000)
 
     # Load book and trade data
-    book_train = pd.read_parquet("/kaggle/input/optiver-realized-volatility-prediction/book_train.parquet")
-    trade_train = pd.read_parquet("/kaggle/input/optiver-realized-volatility-prediction/trade_train.parquet")
+    book_train = pd.read_parquet("/kaggle/input/book_train.parquet").head(1000)
+    trade_train = pd.read_parquet("/kaggle/input/trade_train.parquet").head(1000)
 
     # Merge book and trade data with train_df
     merged_df = pd.merge(train_df, book_train, on=["stock_id", "time_id"], how="left")
     merged_df = pd.merge(merged_df, trade_train, on=["stock_id", "time_id"], how="left")
 
+    print(merged_df.head())
+
     # Split the data
     X = merged_df.drop(["target"], axis=1)
     y = merged_df["target"]
@@ -83,8 +85,19 @@ def preprocess_script():
     X_valid = preprocess_transform(X_valid, preprocessor, numerical_cols, categorical_cols)
 
     submission_df = pd.read_csv("/kaggle/input/test.csv")
-    ids = submission_df["id"]
-    submission_df = submission_df.drop(["id"], axis=1)
+
+    ids = submission_df["row_id"]
+    submission_df = submission_df.drop(["row_id"], axis=1)
+
+    # Add missing columns to submission_df
+    for col in X_train.columns:
+        if col not in submission_df.columns:
+            submission_df[col] = 0  # Fill with 0 or another appropriate value
+
     X_test = preprocess_transform(submission_df, preprocessor, numerical_cols, categorical_cols)
 
+    # Handle missing values
+    for df in [X_train, X_valid, X_test]:
+        df.fillna(df.mean(), inplace=True)
+
     return X_train, X_valid, y_train, y_valid, X_test, ids