Portfolio - Hanif Binginapalli

SQL Project

Phone Sales Analysis Using SQL

Domain/Function: Data Analysis | Ecommerce

This project analyzes smartphone sales data to extract insights such as top-selling brands, revenue trends, and customer behavior using SQL queries. SQL is used to clean, process, and analyze the data from multiple relational tables

View Project
Engagement

View Project
on GitHUB

identidfying the Top 5 most selling Brands

Order status per individual order details

Project Details

Smartphone companies generate large volumes of
sales data, but without proper analysis, it becomes
difficult to understand performance trends.
This project solves the challenge of:
1. Total number of orders
2. Total generated amount per order
3. Highest priced product
4. Top 5 most selling brands
5. Total products per brand
6. OS with highest sales
7. Count orders per order status
8. Count orders per payment method
9. Count orders per customer
10. Products never sold
11. Orders per country and city
12. Monthly orders summary

Python Project

Used Car price prediction web App

Domain/Function: Domain: Automotive Function: Pricing Analytics / Sales Forecasting

Developed a machine learning model to estimate the selling price of used cars based on key features such as brand, year, fuel type, transmission, mileage, and engine specifications. Achieved high accuracy and deployed the model using Streamlit.

View Project
Engagement

View Project
on GitHUB

View Project
on Streamlit

Entering the car details for prediction.

After enter the car details the ml model output.

Project Details

Collected a dataset of 8128 rows from Kaggle containing details of used cars. Cleaned the data using Pandas by handling null values and removing outliers. Applied label encoding to convert categorical features into numerical format. Built a machine learning pipeline using a Random Forest Regressor, trained it on the processed data, and achieved a high R² score of 0.98 on the test set. Developed an interactive web application using Streamlit, allowing users to input car details and instantly get the predicted selling price. The model is deployed and live for real-time predictions.

Project video

Python Project

Predicting Diabetes using ML

Domain/Function: Healthcare

Diabetes Prediction ML App (Healthcare) Developed a web application using Python and Streamlit to predict diabetes risk using patient data and logistic regression, aiding early diagnosis in the healthcare domain.

View Project
on GitHUB

View Project
on Streamlit

Taking user input values

output for the patient data

Project Details

This project focuses on building a machine learning-based web application for predicting the likelihood of diabetes in patients using medical data. The model is trained using the PIMA Indians Diabetes dataset and implemented with Logistic Regression, a suitable algorithm for binary classification problems. The application is developed using Python, Streamlit, and essential data science libraries such as Pandas, Scikit-learn, and Joblib. Users input features like Pregnancies, Glucose Level, Blood Pressure, BMI, and more to get instant predictions on diabetes risk. The interactive UI simplifies access for non-technical users and can assist healthcare professionals in early diagnosis and decision-making. This project highlights the practical use of machine learning in the healthcare domain to improve preventative care and patient awareness.

Python Project

cardiac arrest prediction using machine learning

Domain/Function: Healthcare

This project uses machine learning algorithms to predict the risk of cardiac arrest by analyzing patient health data. It aims to provide early warnings to assist in timely medical intervention and improve patient outcomes.

View Project
on GitHUB

cardiac arrest prediction using machine learning

Entering the patient details

out put for given values

Project Details

Cardiac-Arrest-Prediction

Title : A Machine Learning Approach Using Statistical Models for Early Detection of Cardiac Arrest in Newborn Babies in the Cardiac Intensive Care Unit

Info :This project uses a Logistic Regression model to predict the likelihood of cardiac arrest based on patient health data. The goal is to demonstrate the use of a simple yet
effective machine learning technique for binary classification in a healthcare context.

Over View :Cardiac arrest is a serious medical emergency, and early prediction can help save lives. This project trains a Logistic Regression model on a labeled dataset of patient features to classify whether a cardiac arrest is likely to occur.

features:
Data preprocessing and exploratory data analysis (EDA)
Logistic Regression model for binary classification
Model evaluation using accuracy, confusion matrix, precision, re

PowerBI Project

Title: Business Insights 360 Dashboard for Finance, Sales, Marketing and Supply Chain

Domain/Function: Business

AtliQ Hardwares is growing fast but still uses Excel for reports, which limits smart decision-making. I aim to build a Power BI solution to help the company understand data better and make informed choices.

View Project
Engagement

View Project
on GitHUB

Title: Business Insights 360 Dashboard for Finance, Sales, Marketing and Supply Chain

User-empathetic landing page as a part of dashboard design

Data modelling involving 10+ tables

Project Details

Project Description:

In this project, the goal is to be one report which could be used by stakeholders from sales, marketing, finance and executive team. The focus is made on the following

1. Robust Data Modeling
2. User-empathetic Report design
3. Drillable Insights

I learned the following things in this project

1. Power Query (Basic and Advanced Operations)
2. Basic and complex DAX formulas
3. Data modelling involving 10+ tables
4. Choosing the right visuals and formatting
5. Dashboard designing principles
6. Using bookmarks
7. Deploying in Power BI service
8. Stakeholder Feedback Implementation
9. Sales, Marketing, Finance & Supply Chain metrics

Live Interactive Dashboard

PowerBI Project

Wavecon Telecom Pre & Post 5G Launch Analysis

Domain/Function: Telecom Analytics

This project presents a comprehensive analysis of Wavecon Telecom’s key performance metrics before and after the 5G launch in May 2022, with a focus on assessing its impact on revenue, plan performance, and critical KPIs across 15 major urban centers in India.

View Project
Engagement

View Project
on GitHUB

Wavecon Telecom Pre & Post 5G Launch Analysis

it show the revenue impact on before 5G & After 5G

plan performing well in terms of revenue

Project Details

Project Details
In this project, I analyzed dashboard data to evaluate the business impact of Wavecon Telecom’s 5G rollout.

1. Identified Underperforming KPIs: Assessed key performance indicators that fell short of expectations following the 5G launch.

2. Evaluated Plan Performance: Analyzed revenue trends to determine which plans performed well and which required improvement.

3. Plan Impact Assessment: Examined the influence of 5G on individual plans to recommend continuation, revision, or discontinuation.

4. Discontinued Plan Analysis: Investigated the reasons behind the discontinuation of certain plans after the 5G launch.

5. Actionable Recommendations: Delivered data-driven insights and strategic recommendations to support informed decision-making and future business growth.

Project video

Live Interactive Dashboard

PowerBI Project

Shield Insurance

Domain/Function: Insurance

Shield Insurance is an insurance company offering a variety of policies. It operates in five cities through four different sales modes, with data available from November 2022 to April 2023.

View Project
Engagement

Home Page with 3 navigation page buttons

Over view of total revenue ,customer, DRG, DCG, Customer segmentation, revenue split, age group split, monthly trends of revenue and customer.

Project Details

🔹 Objective :
To help Shield Insurance make better decisions by analyzing data from Nov 2022 – Apr 2023.

🔹 Task :
Build a dashboard that provides key business insights.

🔹 Datasets Used :
◾ Dim Customer
◾ Dim Policies
◾ Dim Date
◾ Fact Premiums
◾ Fact Settlements

🔹 Tools Used :
◾ Microsoft Power BI
◾ Microsoft PowerPoint

🔹 Key Insights :
◾ Delhi NCR had the highest revenue and most customers.
◾ Over 50% of customers prefer offline agents.
◾ POL4321HEL is the cheapest and most popular policy, offering ₹2 lakh coverage.
◾ Age groups 31–40 & 41–50 have the most customers.
◾ Offline sales are dropping, while online sales are growing.
◾ Settlement % is highest for 65+, but 31–40 has the highest expected settlement.
◾ 31–40 age group has the largest customer base (11k customers).

Hello, I am

Hanif Binginapalli

3

3

1

About

Key

My

Phone Sales Analysis Using SQL

Used Car price prediction web App

Predicting Diabetes using ML

cardiac arrest prediction using machine learning

Title: Business Insights 360 Dashboard for Finance, Sales, Marketing and Supply Chain

Wavecon Telecom Pre & Post 5G Launch Analysis

Shield Insurance

Awards

Contact Me

Email

Github

Linkedin

Call

Hanif Binginapalli

Download Resume