diff --git a/backend/tests/test_integration.py b/backend/tests/test_integration.py
index cd41d5c0..f0c25ac0 100644
--- a/backend/tests/test_integration.py
+++ b/backend/tests/test_integration.py
@@ -75,6 +75,20 @@ epc_data = pd.read_csv(
     low_memory=False
 )
 
+# TODO: Store this for cleaning
+costs_by_floor_area = epc_data[
+    pd.to_datetime(epc_data["LODGEMENT_DATE"]) >= "2024-01-01"
+    ][["TOTAL_FLOOR_AREA", "CURRENT_ENERGY_EFFICIENCY", "LIGHTING_COST_CURRENT", "HEATING_COST_CURRENT",
+       "HOT_WATER_COST_CURRENT"]].copy()
+
+costs_by_floor_area.columns = [c.lower().replace("_", "-") for c in costs_by_floor_area.columns]
+for c in ["lighting-cost-current", "heating-cost-current", "hot-water-cost-current"]:
+    costs_by_floor_area[c + "_scaled"] = costs_by_floor_area[c] / costs_by_floor_area["total-floor-area"]
+
+costs_by_floor_area = costs_by_floor_area.groupby("current-energy-efficiency")[
+    ["lighting-cost-current_scaled", "heating-cost-current_scaled", "hot-water-cost-current_scaled"]
+].mean().reset_index()
+
 sample_epc_data = epc_data.drop_duplicates("UPRN").sample(1000).reset_index(drop=True)
 
 # Load the input properties
@@ -140,12 +154,27 @@ for p in tqdm(input_properties):
 mocked_kwh_predictions["heating_kwh_predictions"] = pd.DataFrame(mocked_kwh_predictions["heating_kwh_predictions"])
 mocked_kwh_predictions["hotwater_kwh_predictions"] = pd.DataFrame(mocked_kwh_predictions["hotwater_kwh_predictions"])
 
+# TODO: We might want to implement this generally, via an ETL process
+for p in input_properties:
+    for col in ["lighting-cost-current", "heating-cost-current", "hot-water-cost-current"]:
+        if pd.isnull(p.data[col]):
+            min_diff = abs(
+                (costs_by_floor_area["current-energy-efficiency"] - p.data["current-energy-efficiency"])
+            ).min()
+            df = costs_by_floor_area[
+                abs((costs_by_floor_area["current-energy-efficiency"] - p.data[
+                    "current-energy-efficiency"])) == min_diff
+                ]
+            if df.shape[0] > 1:
+                df = df.head(1)
+            p.data[col] = (df[col + "_scaled"] * p.data["total-floor-area"]).values[0]
+
 [
     p.set_features(cleaned=cleaned, kwh_client=kwh_client, kwh_predictions=mocked_kwh_predictions) for p in
     input_properties
 ]
 
-for p in input_properties:
+for p in tqdm(input_properties):
     # TEMP
     p.DATA_ANOMALY_MATCHES = DATA_ANOMALY_MATCHES
     p.set_features(cleaned=cleaned, kwh_client=kwh_client, kwh_predictions=mocked_kwh_predictions)
diff --git a/etl/epc_clean/epc_attributes/all_cleaners.py b/etl/epc_clean/epc_attributes/all_cleaners.py
index e4e0a0ba..cb9b2b24 100644
--- a/etl/epc_clean/epc_attributes/all_cleaners.py
+++ b/etl/epc_clean/epc_attributes/all_cleaners.py
@@ -17,5 +17,5 @@ all_cleaner_map = {
     'roof-description': RoofAttributes,
     'walls-description': WallAttributes,
     'windows-description': WindowAttributes,
-    'lighting-description:': LightingAttributes,
+    'lighting-description': LightingAttributes,
 }