App Rating Prediction

This project aims to predict the potential boost in visibility for certain apps on the Google Play Store. The new feature being introduced by the Google Play Store team will prioritize certain apps in recommendations sections and search results. This boost in visibility can significantly impact an app's success by attracting more attention from users.

Problem Statement

The Google Play Store team is launching a new feature that boosts the visibility of promising apps. The goal is to identify and prioritize newer apps that have the potential to succeed. The boost will manifest in higher priority in recommendations sections such as "Similar apps", "You might also like", and "New and updated games", as well as increased visibility in search results. The problem statement for this project is to predict the extent of boost an app might receive based on certain features and attributes.

Methodology

• Data Cleaning: The dataset containing information about various apps will be cleaned to remove any inconsistencies or missing values. This ensures the quality of data for analysis and modeling.

• Data Preprocessing: The data will be preprocessed to prepare it for training the model. This may include feature scaling, encoding categorical variables, and handling outliers.

• Model Selection: Linear regression model will be used for predicting the boost in visibility for apps. This model is chosen for its simplicity and interpretability.

• Training and Testing: The model will be trained on a subset of the data and tested on another subset to evaluate its performance. This helps in assessing how well the model generalizes to unseen data.

Results

The results of the model predictions will be displayed, indicating the potential boost in visibility for each app. Evaluation metrics such as mean squared error or R-squared value may also be provided to assess the performance of the model.

Future Improvements

• Explore other machine learning algorithms to compare and improve prediction accuracy.
• Incorporate additional features or data sources to enhance model performance.
• Optimize model hyperparameters for better results.

Contributors

• Avinash Warale
• Siddharth Pagaria
• Asima Siddiqua
• Spoorthi HG
• Chaitra V
• Uday G

Feel free to contribute to this project by forking and submitting pull requests.