diff --git a/modules/ml-pipeline/src/pipeline/configs/feature_processor_logic.py b/modules/ml-pipeline/src/pipeline/configs/feature_processor_logic.py
index 7b131dc..78c29a9 100644
--- a/modules/ml-pipeline/src/pipeline/configs/feature_processor_logic.py
+++ b/modules/ml-pipeline/src/pipeline/configs/feature_processor_logic.py
@@ -18,11 +18,42 @@ def remove_starting_columns(df):
     return df
 
 
+def keep_negative_heat_change(df):
+    df = df[df["HEAT_DEMAND_CHANGE"] < 0]
+    return df
+
+
 def keep_negative_carbon_change(df):
     df = df[df["CARBON_CHANGE"] < 0]
     return df
 
 
+# TODO: Move to ETL pipeline
+def remove_unreasonable_habitable_rooms(df):
+    """
+    Assumption is that proportion of floor area to habitable rooms should be at least 6.5m2
+    """
+    minimum_room_size_index = (
+        df["TOTAL_FLOOR_AREA_ENDING"] / df["NUMBER_HABITABLE_ROOMS"] >= 6.5
+    )
+    df = df[minimum_room_size_index]
+    return df
+
+
+def remove_top_1_percent_heat_demand(df):
+    # threshold_value = df.describe(percentiles=[0.99])['HEAT_DEMAND_STARTING']['99%']
+    threshold_value = 860
+    df = df[df["HEAT_DEMAND_STARTING"] < threshold_value]
+    return df
+
+
+def remove_top_1_percent_carbon(df):
+    # threshold_value = df.describe(percentiles=[0.99])['CARBON_STARTING']['99%']
+    threshold_value = 18
+    df = df[df["CARBON_STARTING"] < threshold_value]
+    return df
+
+
 # def keep_ending_columns(df):
 #     ending_column_index = [ col_name.endswith("_ENDING") for col_name in list(df.columns)]
 #     keep_columns = df.columns[ending_column_index].to_list()
@@ -32,7 +63,11 @@ def keep_negative_carbon_change(df):
 #     return df
 
 business_logic = {
-    "keep_negative_carbon_change": keep_negative_carbon_change
+    "remove_unreasonable_habitable_rooms": remove_unreasonable_habitable_rooms,
+    "keep_negative_heat_change": keep_negative_heat_change,
+    "keep_negative_carbon_change": keep_negative_carbon_change,
+    "remove_top_1_percent_heat_demand": remove_top_1_percent_heat_demand,
+    "remove_top_1_percent_carbon": remove_top_1_percent_carbon,
     # "remove_starting_columns": remove_starting_columns
     # "keep_ENDING_COLUMNS": keep_ending_columns
 }
diff --git a/modules/ml-pipeline/src/pipeline/dvc.lock b/modules/ml-pipeline/src/pipeline/dvc.lock
index 627af99..e65dfe8 100644
--- a/modules/ml-pipeline/src/pipeline/dvc.lock
+++ b/modules/ml-pipeline/src/pipeline/dvc.lock
@@ -29,8 +29,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 73c1f7be21be8358a73c4ab5f9ec8e39.dir
-      size: 32943109
+      md5: ca205aaf77cb9a9414a0c6a1affd8d82.dir
+      size: 30597800
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -41,8 +41,8 @@ stages:
       size: 4149
     - path: data/prepared_data
       hash: md5
-      md5: 73c1f7be21be8358a73c4ab5f9ec8e39.dir
-      size: 32943109
+      md5: ca205aaf77cb9a9414a0c6a1affd8d82.dir
+      size: 30597800
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -68,12 +68,12 @@ stages:
     outs:
     - path: data/model/
       hash: md5
-      md5: dee1a60e6a9f4695272da8127196f714.dir
-      size: 326732699
+      md5: f3be67a0a80e525d30665f2ffc367d9b.dir
+      size: 312133166
       nfiles: 24
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 1fefa99c7bc50d09c31bf175d5b9ee9c
+      md5: 36912d423f975802ca3661992103e614
       size: 226
   generate_predictions:
     cmd: python 3_generate_predictions.py
@@ -84,13 +84,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: dee1a60e6a9f4695272da8127196f714.dir
-      size: 326732699
+      md5: f3be67a0a80e525d30665f2ffc367d9b.dir
+      size: 312133166
       nfiles: 24
     - path: data/prepared_data
       hash: md5
-      md5: 73c1f7be21be8358a73c4ab5f9ec8e39.dir
-      size: 32943109
+      md5: ca205aaf77cb9a9414a0c6a1affd8d82.dir
+      size: 30597800
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -102,8 +102,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: d2da3b713811952b66e2c5f8c95f5407.dir
-      size: 410646
+      md5: 2ae9ab85ca2551d6b0833337cacbcc3e.dir
+      size: 389118
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -114,13 +114,13 @@ stages:
       size: 3485
     - path: data/predictions
       hash: md5
-      md5: d2da3b713811952b66e2c5f8c95f5407.dir
-      size: 410646
+      md5: 2ae9ab85ca2551d6b0833337cacbcc3e.dir
+      size: 389118
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 73c1f7be21be8358a73c4ab5f9ec8e39.dir
-      size: 32943109
+      md5: ca205aaf77cb9a9414a0c6a1affd8d82.dir
+      size: 30597800
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -130,7 +130,7 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 4ed2edc06b4dad3c094a2d1be374a5de
+      md5: 6447c7b2b92a4057aecd3d227de1aadf
       size: 224
   startup_cleanup:
     cmd: python 0_startup_cleanup.py