This project uses Machine Learning Regression to predict your future monthly expenses based on your past spending patterns.

It’s similar to what budgeting apps (like MoneyView, Walnut, YNAB) use.

---

🎯 What This Project Can Do

✔ Learn from your last 6–12 months of expenses
✔ Predict next month’s spending
✔ Show category-wise predictions (food, rent, travel)
✔ Visualize data
✔ Support CSV or SQL database
✔ Optionally build a mobile-friendly Streamlit dashboard

---

📁 Folder Structure

expense_predictor/
│── expense_data.csv
│── train_model.py
│── predict.py
│── model.pkl
│── vectorizer.pkl (if using categories)

---

📊 Example CSV (expense_data.csv)

month,expense
1,12000
2,13000
3,15000
4,14500
5,16000
6,17000

---

🧠 1. ML Model Training (train_model.py)

Using Linear Regression (best for simple numeric trends):

import pandas as pd
from sklearn.linear_model import LinearRegression
import joblib

df = pd.read_csv("expense_data.csv")

X = df[["month"]]
y = df["expense"]

model = LinearRegression()
model.fit(X, y)

joblib.dump(model, "model.pkl")
print("Model trained and saved as model.pkl")

---

🧠 2. Predict Next Month (predict.py)

import joblib
import pandas as pd

df = pd.read_csv("expense_data.csv")
next_month = df["month"].max() + 1

model = joblib.load("model.pkl")
prediction = model.predict([[next_month]])

print(f"Predicted Expense for Month {next_month}: ₹{prediction[0]:.2f}")

---

📈 Optional Enhanced Dataset (category-based)

date,food,travel,rent,shopping,others
2025-01-01,2200,300,8500,0,200
2025-02-01,2500,450,8500,500,300

---

🧠 Advanced ML Version (Multiple Features)

Using RandomForestRegressor for higher accuracy:

from sklearn.ensemble import RandomForestRegressor
import pandas as pd
import joblib

df = pd.read_csv("expense_data.csv")

X = df.drop(columns=["total"])
y = df["total"]

model = RandomForestRegressor()
model.fit(X, y)

joblib.dump(model, "model.pkl")
print("Advanced model trained!")