Skip to content
md ~/projects/bebek-beyin-agirligi-tahmini
Project archive

2026

AI-Powered Baby Brain Weight Prediction System

  • Python
  • Scikit-learn
  • Pandas
  • NumPy
  • Streamlit
  • Plotly
  • SQLite
View on GitHub

Overview

Predicts infant brain weight from head circumference with linear regression. The model is trained on a 70/30 split and evaluated with R², MAE and MSE, and predictions are logged to SQLite through a Streamlit interface.

01 · Problem

An infant's brain weight cannot be measured directly. Can it be predicted from an easy measurement such as head circumference, and how reliable would that prediction be?

02 · Solution

I cleaned the dataset with Pandas, split it 70/30 into training and test sets and trained a linear regression model with scikit-learn. The model makes live predictions in a dashboard I built with Streamlit; the regression line is drawn with Plotly and predictions are saved to SQLite.

03 · Outcome

The model reaches an R² of about 0.66 with a mean absolute error of about 59 grams (y = 0.26x + 354.84). Built as a Machine Learning course project, it covers an end-to-end ML workflow from data preparation to the user interface.