I will do machine learning and ai projects

I deliver the complete source code in highly organized, well-commented Jupyter Notebooks (.ipynb) or standard Python scripts (.py), making it incredibly easy for you to run, review, and modify the workflow.

You will need to provide the dataset or a clean sample of the data you want to use. If you do not have data yet but have a specific project goal, please message me first so we can discuss potential public data sources.

Revisions cover adjustments to model parameters, changing optimization metrics, or tweaking existing code logic. Revisions do not cover swapping out the original dataset for a completely new one midway through the order.

I handle both. For standard tabular data, I typically use highly efficient algorithms like Random Forest or XGBoost. For more complex datasets that require deep learning, I can design and train custom neural networks using TensorFlow and Keras.

Machine learning depends heavily on the quality of the data. If the initial model's performance isn't great, I will use advanced techniques like feature engineering, testing alternative algorithms, and hyperparameter tuning to squeeze out the highest possible score.

Not at all. Real-world data is rarely perfect. Data cleaning and preprocessing like handling missing values, filtering out noise, and formatting columns are fully included in every package before I ever start training a model.