You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The "Advertising Impact Analysis" project aims to analyze the relationship between advertising expenditure across different channels (such as TV, radio, online) and its impact on sales or revenue.
Utilizing advanced Bidirectional LSTM RNN technology, our project focuses on accurately predicting stock market trends. By analyzing historical data, our system learns intricate patterns to provide insightful forecasts. Investors gain a robust tool for informed decision-making in dynamic market conditions. With a streamlined interface, our solution
This repo hosts an end-to-end machine learning project designed to cover the full lifecycle of a data science initiative. The project encompasses a comprehensive approach including data Ingestion, preprocessing, exploratory data analysis (EDA), feature engineering, model training and evaluation, hyperparameter tuning, and cloud deployment.
Utilizando-se a técnica de regressão linear, com o auxílio dos frameworks scikit-learn e statsmodel, foi possível criar um modelo de predição de preços de imóveis, com base em variáveis explanatórias de um database.
Utilizando-se a técnica de regressão linear, com o auxílio do framework scikit-learn, foram realizados dois projetos nos quais foram utilizados dois databases diferentes (um de consumo de cerveja, e outro do preço de imóveis). Utlizando-se ambos, foi possível prever o consumo de cerveja e o preço dos imóveis, com base nas variáveis explanatórias.
Explore the complete lifecycle of a machine learning project focused on regression. This repository covers data acquisition, preprocessing, and training with Linear Regression, Decision Tree Regression, and Random Forest Regression models. Evaluate and compare models using R2 score. Ideal for learning and implementing regression use cases.
This machine learning project focused on predicting food delivery times. The code emphasizes essential tasks such as data cleaning, feature engineering, categorical feature encoding, data splitting, and standardization to establish a solid foundation for building a robust predictive model.
In the digital music era, understanding artist popularity on Spotify is vital. This project taps into Spotify's data, analyzing key factors driving artist prominence. Through our insights, we illuminate what sets successful artists apart in this dynamic platform.
Beta Bank is losing customers monthly. Employees want to focus on client retention. As a Data Scientist, I created a model to predict the chance of a customer leaving, based on past behavior and contract terminations.