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 48a28bf..e93b44b 100644
--- a/modules/ml-pipeline/src/pipeline/configs/feature_processor_logic.py
+++ b/modules/ml-pipeline/src/pipeline/configs/feature_processor_logic.py
@@ -160,7 +160,9 @@ def add_features_from_code(df):
 
     return df
 
-
+def add_estimate_annual_kwh(df):
+    df['estimate_annual_kwh'] = df['energy-consumption-current'] * df['total-floor-area']
+    return df
 
 # def keep_ending_columns(df):
 #     ending_column_index = [ col_name.endswith("_ENDING") for col_name in list(df.columns)]
@@ -172,7 +174,8 @@ def add_features_from_code(df):
 
 business_logic = {
     "add_features_from_code": add_features_from_code,
-    "remove_hotwaterkwh_bottom_percentile": remove_hotwaterkwh_bottom_percentile
+    "remove_hotwaterkwh_bottom_percentile": remove_hotwaterkwh_bottom_percentile,
+    "add_estimate_annual_kwh": add_estimate_annual_kwh
     # "keep_non_zero_rdsap": keep_non_zero_rdsap,
     # "keep_flats": keep_flats,
     # "remove_minimum_habitable_room_size": remove_minimum_habitable_room_size,
diff --git a/modules/ml-pipeline/src/pipeline/configs/settings.yaml b/modules/ml-pipeline/src/pipeline/configs/settings.yaml
index 5fb1d1d..bbf7f23 100644
--- a/modules/ml-pipeline/src/pipeline/configs/settings.yaml
+++ b/modules/ml-pipeline/src/pipeline/configs/settings.yaml
@@ -30,75 +30,9 @@ default:
       subsample_seed: 0
       target: hot_water_kwh
       identifier_columns: ["uprn"]
-      drop_columns: ["heating_kwh"]
-      retain_features: [
-        'uprn', 
-        'heating-cost-current',
-        'co2-emissions-current',
-        'hot-water-cost-current',
-        'total-floor-area',
-        'secondheat-description',
-        'environment-impact-current',
-        'floor-description',
-        'mainheat-energy-eff',
-        'current-energy-efficiency',
-        'mainheat-env-eff',
-        'walls-energy-eff',
-        'roof-energy-eff',
-        'property-type',
-        'mainheat-description',
-        'hot-water-env-eff',
-        'mechanical-ventilation',
-        'floor-level',
-        'built-form',
-        'walls-description',
-        'mainheatcont-description',
-        'roof-description',
-        'energy-consumption-current',
-        'construction-age-band',
-        'hotwater-description',
-        # 'lodgement-datetime',
-        'main-fuel',
-        'hot-water-energy-eff',
-        'co2-emiss-curr-per-floor-area',
-        'windows-energy-eff',
-        'current-energy-rating',
-        'lodgement-year',
-        'extension-count',
-        'number-open-fireplaces',
-        'number-heated-rooms',
-        # 'lodgement-date',
-        #  'number-habitable-rooms',
-        'windows-description',
-        # 'local-authority',
-        'photo-supply',
-        'heat-loss-corridor',
-        # 'posttown',
-        #  'address',
-        'flat-top-storey',
-        'unheated-corridor-length',
-        'fixed-lighting-outlets-count',
-        # 'inspection-date',
-        'tenure',
-        # 'county',
-        # 'constituency-label',
-        'multi-glaze-proportion',
-        'solar-water-heating-flag',
-        #  'address2',
-        'energy-tariff',
-        'floor-height',
-        'constituency',
-        # 'uprn-source',
-        'transaction-type',
-        'floor-energy-eff',
-        # 'postcode',
-        'lodgement-month',
-        'lighting-cost-current',
-        'glazed-area',
-        #  'address1',
-        'floor-env-eff',
-        'main-heating-controls'
-      ]
+      drop_columns: ["heating_kwh", 'lodgement-datetime', 'lodgement-date', 'number-habitable-rooms', 'local-authority', 'posttown', 'address', 'inspection-date',
+      "county", "constituency-label", 'address2', 'uprn-source', 'postcode', 'address1', 'mainheat-env-eff', 'environment-impact-current', 'hot-water-env-eff', 'floor-env-eff']
+      retain_features: null
 
   generate_predictions:
     input_dataclient_type: local
diff --git a/modules/ml-pipeline/src/pipeline/dvc.lock b/modules/ml-pipeline/src/pipeline/dvc.lock
index 06f4eb4..a52895f 100644
--- a/modules/ml-pipeline/src/pipeline/dvc.lock
+++ b/modules/ml-pipeline/src/pipeline/dvc.lock
@@ -22,60 +22,24 @@ stages:
       configs/settings.yaml:
         default.feature_processor.feature_processor_config.drop_columns:
         - heating_kwh
-        default.feature_processor.feature_processor_config.retain_features:
-        - uprn
-        - heating-cost-current
-        - co2-emissions-current
-        - hot-water-cost-current
-        - total-floor-area
-        - secondheat-description
-        - environment-impact-current
-        - floor-description
-        - mainheat-energy-eff
-        - current-energy-efficiency
+        - lodgement-datetime
+        - lodgement-date
+        - number-habitable-rooms
+        - local-authority
+        - posttown
+        - address
+        - inspection-date
+        - county
+        - constituency-label
+        - address2
+        - uprn-source
+        - postcode
+        - address1
         - mainheat-env-eff
-        - walls-energy-eff
-        - roof-energy-eff
-        - property-type
-        - mainheat-description
+        - environment-impact-current
         - hot-water-env-eff
-        - mechanical-ventilation
-        - floor-level
-        - built-form
-        - walls-description
-        - mainheatcont-description
-        - roof-description
-        - energy-consumption-current
-        - construction-age-band
-        - hotwater-description
-        - main-fuel
-        - hot-water-energy-eff
-        - co2-emiss-curr-per-floor-area
-        - windows-energy-eff
-        - current-energy-rating
-        - lodgement-year
-        - extension-count
-        - number-open-fireplaces
-        - number-heated-rooms
-        - windows-description
-        - photo-supply
-        - heat-loss-corridor
-        - flat-top-storey
-        - unheated-corridor-length
-        - fixed-lighting-outlets-count
-        - tenure
-        - multi-glaze-proportion
-        - solar-water-heating-flag
-        - energy-tariff
-        - floor-height
-        - constituency
-        - transaction-type
-        - floor-energy-eff
-        - lodgement-month
-        - lighting-cost-current
-        - glazed-area
         - floor-env-eff
-        - main-heating-controls
+        default.feature_processor.feature_processor_config.retain_features:
         default.feature_processor.feature_processor_config.subsample_amount:
         default.feature_processor.feature_processor_config.subsample_seed: 0
         default.feature_processor.feature_processor_config.target: hot_water_kwh
@@ -90,8 +54,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 295ac4fd05a1a3373401a7318b0b5186.dir
-      size: 13131853
+      md5: 0364b2ef5dd7674f97473fdecf3f3a02.dir
+      size: 35173792
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -102,8 +66,8 @@ stages:
       size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: 295ac4fd05a1a3373401a7318b0b5186.dir
-      size: 13131853
+      md5: 0364b2ef5dd7674f97473fdecf3f3a02.dir
+      size: 35173792
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -135,17 +99,17 @@ stages:
     outs:
     - path: data/fit_predictions/
       hash: md5
-      md5: 3e48cec68f702bc822eed8fcb2c5c603.dir
-      size: 1787931
+      md5: 56598af2325ec699349cdb166b1e807b.dir
+      size: 1789771
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: 37f7480141e920c68faacd39478a1a68.dir
-      size: 451364406
-      nfiles: 35
+      md5: ce995d18c2f40aefe1f5757d621bb4d4.dir
+      size: 592064916
+      nfiles: 36
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: e7a2a5efea57b1ddd1431b713d78bb11
+      md5: 4c169dc1d437e5fea43e47616f46dafc
       size: 219
   generate_predictions:
     cmd: python 3_generate_predictions.py
@@ -156,13 +120,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: 37f7480141e920c68faacd39478a1a68.dir
-      size: 451364406
-      nfiles: 35
+      md5: ce995d18c2f40aefe1f5757d621bb4d4.dir
+      size: 592064916
+      nfiles: 36
     - path: data/prepared_data
       hash: md5
-      md5: 295ac4fd05a1a3373401a7318b0b5186.dir
-      size: 13131853
+      md5: 0364b2ef5dd7674f97473fdecf3f3a02.dir
+      size: 35173792
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -174,8 +138,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 9267a66c6fae4da5a589faab76fac14c.dir
-      size: 192482
+      md5: 590da9bdeb1e1b442e52bce52f1da0dc.dir
+      size: 192586
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -186,13 +150,13 @@ stages:
       size: 3484
     - path: data/predictions
       hash: md5
-      md5: 9267a66c6fae4da5a589faab76fac14c.dir
-      size: 192482
+      md5: 590da9bdeb1e1b442e52bce52f1da0dc.dir
+      size: 192586
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 295ac4fd05a1a3373401a7318b0b5186.dir
-      size: 13131853
+      md5: 0364b2ef5dd7674f97473fdecf3f3a02.dir
+      size: 35173792
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -202,7 +166,7 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 3a08c29f028f5e3cb50fb8cd3608e2f4
+      md5: b80014eacb59a824aff78667352e7c95
       size: 221
   generate_scenerio_metrics:
     cmd: python 5_generate_scenarios.py