8 skills found
Kunal-Attri / Malware Detection ML ModelThis is a Malware Detection ML model made using Random Forest Algorithm
timothygmitchell / Empirical Study Of Ensemble Learning MethodsTraining ensemble machine learning classifiers, with flexible templates for repeated cross-validation and parameter tuning
emirhanai / AID362 Bioassay Classification And Regression Neuronal Network And Extra Tree With Machine LearninI developed Machine Learning Software with multiple models that predict and classify AID362 biology lab data. Accuracy values are 99% and above, and F1, Recall and Precision scores are average (average of 3) 78.33%. The purpose of this study is to prove that we can establish an artificial intelligence (machine learning) system in health. With my regression model, you can predict whether it is Inactive or Inactive (Neural Network or Extra Trees). In classification (Neural Network or Extra Trees), you can easily classify the provided data whether it is Inactive or Active.
sidharth178 / Credit Risk Analysis Using LightGBM ClassifierThe objective of this project is to determine the risk of default that a client presents and assign a risk rating to each client. The risk rating will determine if the company will approve (or reject) the loan application
mdaiyub / Diabetes PredictionDiabetes mellitus, commonly known as diabetes is a metabolic disease that causes high blood sugar. The hormone insulin moves sugar from the blood into your cells to be stored or used for energy. With diabetes, your body either doesn’t make enough insulin or can’t effectively use its insulin.
a3X3k / Spam Email DetectionNo description available
JLFDataScience / Jane Street Market PredictionJane Street Competition in Kaggle: Approach with PyCaret and training of the best model - ExtraTreesClassifier | PCA | Pipeline
Mubshr07 / HeartDiseasePredictionThis repo is the Machine Learning practice on NHANES dataset of Heart Disease prediction. The ML algorithms like LR, DT, RF, SVM, KNN, NB, MLP, AdaBoost, XGBoost, CatBoost, LightGBM, ExtraTree, etc. The results are good. I also explore the class-balancing (SMOTE) because the original dataset contains only 5% of patient and 95% of healthy record.
