ML Job Market Project

AI-Powered Job Market Predictor uses Kaggle data, Pandas for preprocessing, Scikit-Learn for ML predictions, and Matplotlib for visual insights, showcasing machine learning in job market analysis.

Comment

Inspiration

AI is rapidly transforming the tech world, automating tasks once thought too complex for machines. We wanted to explore how different jobs could be impacted by this trend and highlight which roles might be most vulnerable to automation by AI.

What it does

Our “ML Job Market Project” predicts the level of impact AI might have on various job titles. It takes a dataset of roles (e.g., tech jobs, administrative positions, etc.), cleans and processes the data, trains a machine learning model to learn from examples, and then provides a percentage score indicating each job’s susceptibility to AI automation. The project also includes interactive visualizations comparing actual versus predicted AI impact.

How we built it

  1. Data Preparation & Cleaning: We gathered a dataset with known AI impact values and cleaned columns by removing unwanted characters (like “%” signs) and handling missing values.
  2. Feature Engineering: Non-numeric features were converted to numeric using one-hot encoding to make them suitable for a machine learning model.
  3. Model Training: A Random Forest Regressor was trained on the cleaned and scaled dataset to predict the AI impact.
  4. Prediction & Visualization: A second dataset without known AI impact values was processed through the same pipeline, and predictions were visualized side by side with the original training data ## Challenges we ran into Scatter Plot Visualization: Ensuring the subplots lined up neatly and the hover text displayed useful information took some trial and error. Understanding ML: Getting comfortable with concepts like one-hot encoding, scaling data, and interpreting metrics like MSE and R² required time and practice. ## Accomplishments that we're proud of We successfully built an end-to-end machine learning pipeline: from data ingestion to model training, prediction, and interactive visualization. Having an easy-to-interpret final plot of both actual and predicted AI impacts is a highlight of the project. ## What we learned This project taught us how crucial data cleaning, preprocessing, and feature engineering are in any ML workflow. We also gained experience in evaluating model performance and implementing visualizations that make our predictions more understandable. ## What's next for ML Job Market Project Experiment with different machine learning algorithms or hyperparameter tuning to optimize the predictions further.
Share this project:

Updates