The Resume Classification Project is designed to automate the process of categorizing resumes into four distinct categories. By leveraging advanced machine learning techniques, this solution aims to significantly reduce the manual effort involved in the HR management process. The project focuses on achieving high accuracy and a high level of automation with minimal human intervention.

The primary goal of this project is to:

• Minimize the manual effort required in resume classification within HR management.
• Achieve a high level of accuracy in classifying resumes.
• Implement a scalable solution with minimal human intervention.

• Data Analysis and Preprocessing: Exploratory Data Analysis (EDA) using Pandas.
• Text Processing: Tokenization and text processing using the NLTK library.
• Vectorization: TF-IDF vectorization for transforming text data into numerical features.
• Machine Learning Models: Implementation of various ensemble and bagging techniques using Scikit-Learn.
• Deployment: Deployment of the application using Streamlit on the cloud.

EDA was conducted using Pandas to understand the data distribution, identify patterns, and clean the data for modeling. Key steps included:

• Loading and inspecting the dataset.
• Handling missing values.
• Normalizing text data.

Text processing was performed using the NLTK library. Key steps included:

• Tokenization: Breaking down the text into tokens.
• Stopwords Removal: Removing common stop words to focus on significant words.
• Lemmatization: Reducing words to their base or root form.

TF-IDF (Term Frequency-Inverse Document Frequency) vectorizer was used to convert text data into numerical features suitable for machine learning models. This helps in understanding the importance of words in the context of the document corpus.

Various machine learning models were implemented using Scikit-Learn, focusing on ensemble and bagging techniques to enhance model performance:

• Random Forest
• Gradient Boosting
• AdaBoost
• Bagging Classifier

Hyperparameter tuning and cross-validation were performed to optimize model performance.

The final model was deployed using Streamlit, a popular framework for creating interactive web applications. The application is hosted on the cloud, providing an accessible and user-friendly interface for HR professionals to classify resumes efficiently.

vevekkottapally123@gmail.com