Skip to content

ryanlharper/Data-Science

Repository files navigation

Data Science Projects

Welcome to my repository showcasing various data science projects. Each project explores different methods and techniques within the field of data science.

Projects

Dynamic Pricing Strategy for Used Devices

Objective: Analyze the used devices dataset, develop a model for dynamic pricing, and identify key factors influencing the price of used and refurbished devices.

Skills & Tools Covered:

  • Exploratory Data Analysis (EDA)
  • Linear Regression
  • Linear Regression Assumptions

Predictive Modeling for Booking Cancellations

Objective: Analyze the data of INN Hotels to identify factors influencing booking cancellations. Build a predictive model capable of forecasting cancellations in advance, aiding in the formulation of profitable cancellation and refund policies.

Skills & Tools Covered:

  • Exploratory Data Analysis (EDA)
  • Data Preprocessing
  • Logistic Regression
  • Multicollinearity
  • AUC-ROC Curve
  • Decision Tree
  • Pruning

Predictive Modeling for Visa Approvals

Objective: Analyze the data of Visa applicants, construct a predictive model to streamline the visa approval process, and recommend suitable profiles for certification or denial based on crucial factors influencing Visa status.

Skills & Tools Covered:

  • Exploratory Data Analysis (EDA)
  • Data Preprocessing
  • Customer Profiling
  • Bagging Classifiers (Bagging and Random Forest)
  • Boosting Classifiers (AdaBoost, Gradient Boosting, XGBoost)
  • Stacking Classifier
  • Hyperparameter Tuning using GridSearchCV
  • Business Insights

Predictive Maintenance for Wind Turbine Generators

Objective: ReneWind, a company dedicated to enhancing the machinery and processes in wind energy production, has collected data on generator failures in wind turbines using sensors. The goal is to build, tune, and identify the best classification model to predict failures. This enables timely repairs, reducing overall maintenance costs and preventing generator breakdowns.

Skills & Tools Covered:

  • Up and Downsampling
  • Regularization
  • Hyperparameter Tuning

Clustering for Stocks

Objective: Analyze stock data, grouping the stocks based on the attributes provided, and sharing insights about the characteristics of each group. Skills & Tools Covered:

  • Kmeans Clustering
  • Hierarchical Clustering
  • Cluster Profiling