📈 Bank Marketing Campaign: Evaluating Classifier Algorithms for Term Deposit Subscriptions Prediction
Welcome to the GitHub repository for a data analytics project focused on evaluating and identifying the best classifier algorithm for predicting client term deposit subscriptions in a Kaggle bank marketing dataset.
This project centers around an extensive analysis of the bank marketing dataset, obtained from Kaggle. The dataset contains a wealth of information about client demographics, past marketing campaigns, and various attributes that influence their subscription decisions.
The primary objective of this project is to assess and compare different classifier algorithms to determine the most accurate and reliable model for predicting whether a client will subscribe to a term deposit or not. By leveraging the dataset's features and the power of machine learning, we aim to provide valuable insights for campaign optimization and strategic decision-making.
Throughout this project, we explore and evaluate a range of classifier algorithms, including but not limited to logistic regression, decision trees, and k-neighbors. By implementing these algorithms and carefully tuning their hyperparameters, we strive to identify the algorithm that yields the highest prediction accuracy and performance.
- Thorough exploration and analysis of the Kaggle bank marketing dataset.
- Implementation and evaluation of various classifier algorithms.
- Tuning of hyperparameters for optimal model performance.
- Documentation of methodologies, results, and code for transparency and reproducibility.
We tested this dataset using 3 different classifiers (LogisticRegression, KNeighborsClassifier, and DecisionTreeClassifier) to see which classifiers generates the most accurate prediction. From our cross-validation, LogisticRegression generates the most accurate prediction, which is 90% of accuracy.