This repository contains a Machine Learning model that predicts the comprehensive strength of concrete. The model uses various features such as cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, and fine aggregate to make accurate predictions. The goal of this project is to help in understanding the key factors that influence the comprehensive strength of concrete.
-
Data Preprocessing: The initial step involved cleaning the data, handling missing values, and encoding categorical variables to prepare the dataset for model training.
-
Model Training: I experimented with different machine learning algorithms including Random Forests, Gradient Boost, Ada Boost and K-Nearest-Neighbors. Each model was trained and validated using cross-validation to ensure the model’s robustness
-
Model Evaluation: The models were evaluated based on their accuracy in predicting the strength of unseen data. Performance metrics such as R-squared were used for this purpose.
This project was an exciting opportunity to apply machine learning concepts to a practical problem in the construction industry. It was particularly interesting to see how different algorithms performed on the same task and how model performance can be optimized.
I’m looking forward to exploring more ways to leverage machine learning in the future.
I'm a Full Stack Data Scientist
- C, C++, Python
- SQL
- Machine Learning
- Deep Learning
- Data Science
👩💻 I'm currently a student
🧠 Btech Computer Science
💬 more details loading