diff --git a/matching-model/.DS_Store b/matching-model/.DS_Store
new file mode 100644
index 0000000..b06b76a
Binary files /dev/null and b/matching-model/.DS_Store differ
diff --git a/matching-model/convertDStoCSV.py b/matching-model/convertDStoCSV.py
new file mode 100644
index 0000000..68cc9ef
--- /dev/null
+++ b/matching-model/convertDStoCSV.py
@@ -0,0 +1,22 @@
+# Converts the datatset into csv file  - i.e the donations table is being converted into .csv file
+
+import pandas as pd
+from your_flask_app import app, db  # Import your Flask app and SQLAlchemy objects
+from models import Donation  # Import the Donation model
+
+def export_to_csv():
+    with app.app_context():
+        donations = Donation.query.all()
+        data = [{
+            'food_type': donation.food_type,
+            'quantity': donation.quantity,
+            'location': donation.location,
+            'timestamp': donation.timestamp
+        } for donation in donations]
+
+        df = pd.DataFrame(data)
+        df.to_csv('donations_requests.csv', index=False)
+
+# Call this function periodically, e.g., using a cron job or a scheduled task
+export_to_csv()
+
diff --git a/matching-model/main.py b/matching-model/main.py
new file mode 100644
index 0000000..f461500
--- /dev/null
+++ b/matching-model/main.py
@@ -0,0 +1,50 @@
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.metrics.pairwise import cosine_similarity
+
+# Load the CSV file into a pandas DataFrame (assuming data is already loaded)
+df = pd.read_csv('convertDStoCSV.csv')
+
+# Preprocess the data (e.g., handle missing values, encode categorical variables)
+# Assuming 'timestamp' is in string format, convert it to datetime if needed
+df['timestamp'] = pd.to_datetime(df['timestamp'])
+
+# Split the data into features (X) and target variable (y)
+X = df[['food_type', 'location', 'quantity', 'timestamp']]  # Features: food_type, location, quantity, timestamp
+y = df['food_preferences']  # Target variable: food_preferences
+
+# Encode categorical variables (if needed)
+X_encoded = pd.get_dummies(X, columns=['food_type', 'location'], drop_first=True)  # One-hot encoding for categorical variables
+
+# Split the data into training and testing sets
+X_train, X_test, y_train, y_test = train_test_split(X_encoded, y, test_size=0.2, random_state=42)
+
+# Initialize the KNN classifier
+knn = KNeighborsClassifier(n_neighbors=3)  # Adjust hyperparameters as needed
+
+# Train the classifier
+knn.fit(X_train, y_train)
+
+# Calculate similarity between donors and recipients
+def calculate_similarity(row):
+    donor_food = row['food_type'].split(', ')
+    recipient_food = row['food_preferences'].split(', ')
+    vector_donor = [1 if food in donor_food else 0 for food in set(donor_food + recipient_food)]
+    vector_recipient = [1 if food in recipient_food else 0 for food in set(donor_food + recipient_food)]
+    similarity = cosine_similarity([vector_donor], [vector_recipient])[0][0]
+    return similarity
+
+# Calculate similarity scores for the test set
+X_test_similarity = X_test.apply(calculate_similarity, axis=1)
+
+# Set a similarity threshold to filter matches
+threshold = 0.5
+matched_indices = X_test_similarity[X_test_similarity >= threshold].index
+
+# Get the matched donor-recipient pairs
+matched_pairs = df.iloc[matched_indices]
+
+# Output matched pairs along with their similarity scores
+print("Matched Donor-Recipient Pairs:")
+print(matched_pairs[['donor_id', 'recipient_id', 'location', 'quantity']])