Bug priority prediction using HYBRID ML and DL algorithms This project aims to predict the priority level of software bugs by combining textual and tabular features using a hybrid deep learning model based on RNN (Recurrent Neural Network) and MLP (Multi-Layer Perceptron). The system assists developers and triagers by automatically classifying bug reports, helping teams focus on the most critical issues first.
Python, Jupyter Notebook TensorFlow / Keras Scikit-learn, Pandas, NumPy NLTK for NLP preprocessing SMOTE for class balancing TF-IDF for feature vectorization Matplotlib / Seaborn for visualizations