LinkedIn Predictor App
This app is used in predicting LinkedIn user profiles! This interactive tool is a showcase of how personal demographic information can be used to provide insights into whether a person is a LinkedIn user. Here's a brief overview of what you'll see:
- Income Range Selection: Demonstrates how different income levels can influence LinkedIn predictions.
- Education Level Input: Shows the impact of educational attainment on professional networking.
- Parental and Marital Status Indicators: Reflects how personal life choices might affect career opportunities.
- Gender Identification: Highlights how gender can play a role in professional experiences.
- Age Update: Emphasizes the importance of age in career stage predictions.
This app is a personal project designed to demonstrate my abilities in creating predictive models using machine learning and interactive tools using streamlit.io.
Click the link to view app!!
Telecom Customer Churn Rate
This app is used in predicting Telecom Customer Churn Rates. This internal application is designed to help us understand and predict customer churn based on various factors. Here's how it works:
- Select Customer State: Identify the state the customer resides in, starting with 'AL' for Alabama.
- Customer Tenure: Input the number of months the customer has been with us to gauge loyalty.
- Area Code Selection: Choose the customer's area code, like '408', to note regional attributes.
- International Plan: Indicate whether the customer has an international plan to understand service preferences.
- Voicemail Plan: Specify if the customer subscribes to a voicemail plan, offering insights into feature utilization.
- Voicemail Usage: Input the number of voicemails the customer has to measure engagement.
- Total Day Minutes & Calls: Record how many minutes and calls the customer makes during the day to gauge primary usage.
- Day, Evening, and Night Charges: Enter the total minutes, calls, and respective charges during day, evening, and night periods to understand usage patterns.
- International Usage: Detail the customer's international minutes and calls to understand global connectivity.
- Customer Service Calls: Note the number of times the customer has reached out for support.
This tool is great for analyzing customer behavior and identifying potential churn risks. By inputting the respective data, we can better understand usage patterns, preferences, and overall satisfaction, aiding in tailored customer retention strategies. This tool is for internal use and aids in decision-making processes related to customer relationship management.
This app is a personal project designed to demonstrate my abilities in creating predictive models using machine learning and interactive tools using streamlit.io.