Financial Portfolio Optimization Algorithms

Decision Tree classifier from scratch without any machine learning libraries

The objective of this work is to provide tools to be used for the classification of ordinal categorical distributions. To demonstrate how to do it, we propose an Homogeneity (HI) and Location (LI) Index to measure the concentration and central value of an ordinal categorical distribution.

Decision Tree Implementation from Scratch

Algorithms and Data Structures for Data Science and Machine Learning

EDA project for GDP, Inflation, Income Per Capita, Income Inequality in Egypt (1961-2020)

Classification of Data Using Decision Tree and Random Forest

Using pyhthon with pandas and scikit-learn libraries to split, train, test and check the accuracy of DecisionTree model on top of diabetes dataset

Gini Index based sparse signal recovery algorithm

Contains KNN regression, Linear regression, KNN classification and Decision trees (using gini index, entropy & misclassification rate), all implemented from scratch.

Assignments and Project from NJIT CS 675

Decision Tree Classification via CART Algorithm

Décorticage les jeux de données commerciale pour faciliter la prise de décision appuyée sur data: sortir les business insights, identifier les anomalies et des opportunités

Fast computation of the Gini coefficient

Udacity Project 1 - Investigate economic, inequality, & corruption data. This project sets out to find a relationship between the fastest-growing countries, corruption, & inequality.

The AdaBoost algorithm is an ensemble learning method that combines multiple weak learners (base estimators) to create a stronger predictive model.

Content: Root node, Decision node & Leaf nodes, Attribute Selection Measure (ASM), Feature Importance (Information Gain), Gini index

Here are some projects based on static methods of information processing. There are many different methods that you can use to process your information, depending on your needs.

Implemented a Decision Tree from Scratch using binary univariate split, entropy, and information gain. Used Gini index and Pruning for performance improvement.