Predictive Analytics

Multiple linear regression model implementation with automated backward elimination (with p-value and adjusted r-squared) in Python and R for showing the relationship among profit and types of expenditures and the states.

Apply unsupervised learning techniques to identify customers segments.

Trying to predict which species are most threatened with extinction in the near future.

Embedding

Imbalanced Classes, Resampling techniques, filling null value, Date,Time, Alphanumeric data

Car Price Prediction

Predict employee attrition using LogisticRegression and RandomForestClassifier.

Repositorio para los desafíos y trabajos prácticos de la materia de Aprendizaje Automático, donde se implementan y resuelven problemas utilizando técnicas y algoritmos del campo.

Data cleaning tools, handling missing data, categorical data, feature scaling

This project predicts whether a person survived the Titanic disaster based on various features using machine learning. It utilizes pipelines, ColumnTransformer, and model serialization for efficient processing and prediction.

OneHotEncoder : Kategorik verileri "binary" (0 ve 1) sütunlarına ayırır. Her benzersiz kategori için ayrı bir sütun oluşturur. Özellikle sıralı olmayan kategorik değişkenler için uygundur.

pipelines chains together multiple steps so that the output of each step is used as input to the next step

To predict whether a user will click on ad or not.

scikit_learn

In this exploratory data analysis, we compare a dataset which consists of various features about renting of houses available on these renting platforms listed by owners of these houses, and try to derive some constructive conclusions by performing Descriptive statistics of the available features.

Machine learning and neural networks used to create a binary classifier capable of predicting whether applicants will be successful if funded by Alphabet Soup.

Create a binary classification model using a deep neural network

This project presents a comprehensive car price prediction model using machine learning techniques. The dataset is carefully explored and preprocessed, including handling missing values, encoding categorical features, and scaling numerical data. Visualizations are provided to understand key relationships and trends in car features and prices.