diff --git a/modules/ml-pipeline/src/pipeline/eda.py b/modules/ml-pipeline/src/pipeline/eda.py
index 1260d09..de1ebd6 100644
--- a/modules/ml-pipeline/src/pipeline/eda.py
+++ b/modules/ml-pipeline/src/pipeline/eda.py
@@ -175,3 +175,55 @@ plot_permutation_importance(exp, fig_kw={"figwidth": 7, "figheight": 6})
 # Use shap package to explain why 9158 has a 35 prediction when its sap ending is 96
 #
 #
+
+from core.MLModels import model_factory
+from core.DataClient import dataclient_factory
+import pandas as pd
+from config import settings
+
+client_params = settings.client
+prepare_data_params = settings.prepare_data
+feature_process_params = settings.feature_processor
+build_model_params = settings.build_model
+generate_predictions_params = settings.generate_predictions
+prediction_analysis_params = settings.prediction_analysis
+model = model_factory(build_model_params["model_type"])
+model.load_model(build_model_params["model_save_filepath"])
+dataclient_type = prediction_analysis_params["dataclient_type"]
+dataclient = dataclient_factory(
+    dataclient_type=dataclient_type,
+    dataclient_config=client_params[dataclient_type],
+)
+
+target = feature_process_params["feature_processor_config"]["target"]
+predictions_column_name = generate_predictions_params["predictions_column_name"]
+output_test_filepath = prepare_data_params["output_test_filepath"]
+predictions_output_filepath = generate_predictions_params["predictions_output_filepath"]
+
+test_df = dataclient.load_data(output_test_filepath)
+predictions = dataclient.load_data(predictions_output_filepath)
+mix_df = pd.concat([test_df.copy(), predictions], axis=1)
+mix_df["residual"] = abs(mix_df[predictions_column_name] - mix_df[target])
+mix_df = mix_df.sort_values("residual", ascending=False)
+
+cosine_similarity_df = mix_df[
+    mix_df.columns.difference(["predictions", "residual", "SAP_ENDING"])
+]
+from sklearn.metrics.pairwise import cosine_similarity
+
+row_index = 12624
+
+from sklearn.preprocessing import LabelEncoder
+
+object_columns = cosine_similarity_df.select_dtypes(["object"])
+
+cosine_similarity_df[object_columns.columns] = cosine_similarity_df[
+    object_columns.columns
+].apply(LabelEncoder().fit_transform)
+
+feature_vector = cosine_similarity_df.loc[[row_index]]
+
+cosine_similarity_df["cosine"] = cosine_similarity(cosine_similarity_df, feature_vector)
+similar_index = cosine_similarity_df[cosine_similarity_df["cosine"] > 0.997].index
+
+check_df = mix_df.loc[similar_index]