Real world data science projects to become data scientist

Name: Real world data science projects to become data scientist
Rating: 4.3 (4 reviews)

Data science portfolio: Churn Prediction, Insurance Pricing, Sales Forecasting with Logistic Regression & XGBoost

Created byVinay Karode

Last updated 7/2024

English

What you'll learn

Predict customer churn using logistic regression and decision trees.
Understand and apply ensemble learning techniques for better prediction accuracy.
Develop insurance pricing models using XGBoost and evaluate their performance.
Forecast sales for large retail stores with real-world datasets and advanced techniques.
Gain practical experience with real-world data and industry-standard tools.
Learn to interpret model results and make data-driven business decisions.
Enhance your data visualization skills to communicate insights effectively.

Course content

5 sections • 32 lectures • 5h 41m total length

Intro2:34
Explore logistic regression as a foundational machine learning algorithm, its intuition, evaluation metrics, and real-world lifecycle from data pipelines to production with Python and MLflow.
1 introduction logistic regression7:55
2 confusion matrix6:22
3 roc auc3:24
4 code walkthrough42:05
outro1:02
Miro Board0:01

1 intro3:02
Explore classification with decision trees and logistic regression on a telco churn dataset using scikit-learn and MLflow, compare models, and understand when trees excel.
1 What are decision trees3:24
2 Measure of impurity6:01
The lecture explains the measure of impurity in decision trees using the Gini index. It shows how to compute node and split impurity and determine the split by Gini gain.
3 Types of decision trees8:50
4 Code walkthrough35:00
Walk through code to analyze telco churn with MLflow, encode categorical features, balance data with SMOTE, and compare logistic regression and decision trees using ROC AUC and feature importance.
outro1:12

0 introduction to ensemble learning0:46
1 Bagging vs Boosting7:01
2 Random forest inner working2:34
3 AdaBoost inner working11:52
4 gradient boosting inner working9:02
5 code walkthrough21:05
6 LIME10:20
outro2:05
Explore ensemble learning methods, including random forest, AdaBoost, and gradient boosting, and interpret models with LIME, applied to a telco churn dataset, with MLflow tracking and production considerations.

0. intro2:49
1 Exploratory data analysis20:50
2 introduction to correlation1:40
3 correlation code walkthrough18:42
4 base linear model28:53
Learn a base linear regression, extend to multiple linear regression, and evaluate with residuals, normality, and homoscedasticity, using one hot encoding, Yeo-Johnson power transforms, and rmse/r-squared.
5 XGBoost training12:44
6 model evaluation3:30
7 outro1:22
Conclude the project by comparing XGBoost with a linear model, review exploratory data analysis, collinearity, correlation, chi-squared, ANOVA, and multiple linear regression, and outline evaluation metrics for future projects.

Requirements

Basic understanding of Python programming.
Familiarity with fundamental statistics and probability concepts.
Experience with basic data manipulation and visualization libraries like pandas and matplotlib.
Basic knowledge of machine learning concepts is a plus, but not required.

Description

Are you ready to transform your data science skills and tackle real-world challenges? Welcome to "Real World Data Science Projects to Become Data Scientist," a hands-on course designed to equip you with the knowledge and practical experience needed to excel in the field of data science.

In this course, you'll dive deep into five comprehensive projects, each focusing on a crucial aspect of data science:

Churn Prediction Using Logistic Regression and Decision Trees: Learn to predict customer churn by implementing logistic regression and decision tree models. Understand key concepts like the confusion matrix, ROC-AUC, and the importance of evaluating model performance.
Ensemble Learning for Churn Prediction: Discover the power of ensemble learning techniques. Explore bagging, boosting, Random Forest, AdaBoost, and gradient boosting. Gain hands-on experience with model interpretation using LIME.
Insurance Price Prediction Using XGBoost: Develop and evaluate insurance pricing models. Conduct exploratory data analysis, understand correlations, and build robust models using XGBoost. Learn to interpret the results to make data-driven business decisions.
Bigmart Sales Prediction: Forecast sales for large retail stores using advanced techniques. Gain insights from real-world datasets and apply machine learning models to predict future sales accurately.

Throughout the course, you'll work with real datasets and industry-standard tools, enhancing your practical skills. You'll also learn to visualize data, interpret model results, and communicate insights effectively.

This course is perfect for aspiring data scientists, current professionals looking to upgrade their skills, and anyone interested in building a strong portfolio of data science projects. Basic knowledge of Python and familiarity with fundamental statistics are recommended.

Enroll now and take the first step towards mastering data science with real-world projects!

Who this course is for:

Aspiring data scientists looking to gain hands-on experience with real-world projects.
Current data professionals aiming to enhance their predictive modeling skills.
Students and learners who want to build a strong portfolio of data science projects.
Data enthusiasts who want to transition into a data science career.
Business analysts seeking to incorporate data science techniques into their work.
Students in computer science or related fields looking to enhance their skill set.

Real world data science projects to become data scientist

What you'll learn

Explore related topics

Course content

Project 1 : Churn prediction using logistic regression7 lectures • 1hr 3min

Project 2 : Churn prediction using Decision Trees6 lectures • 57min

Project 3 : Ensemble learning for churn prediction8 lectures • 1hr 5min

Project 4: Insurance price prediction using XGBoost8 lectures • 1hr 31min

Project 5 - Bigmart sales prediction3 lectures • 1hr 5min

Requirements

Description

Who this course is for: