Project Details

Developed a targeted Power BI dashboard to address Atliq Grands' challenges of declining market share and revenue. Utilizing three months of data, the dashboard provided valuable insights into the underlying causes of these losses.

The Revenue team gained actionable insights into revenue trends, empowering them to devise strategic initiatives to reverse the downward trajectory. Leveraging these insights, Atliq Grands aims to reclaim 20% of their revenue and market share within the next month, signaling a commitment to sustainable growth and competitiveness.

Live Interactive Dashboard

Project Details

The project aims to analyze key indicators within pizza sales data to derive actionable insights into business performance. By implementing a structured and data-driven approach, the objective is to comprehensively assess relevant metrics, enabling a deeper understanding of business dynamics. This initiative serves to enhance decision-making processes, optimize operational efficiency, and drive overall success in the competitive pizza market.

Learnings from the Project:
- Extracting SQL queries as per requirements.
- Performing data cleaning and transformation.
- Utilizing DAX.
- Creating visually appealing visuals and dashboards.

Insights:
- Busiest orders occur on holiday evenings.
- Peak orders are observed in June and July.
- Classic pizza is the most ordered category.
- Maximum revenue is generated from chicken pizza.
- Brie carre pizza contributes the least revenue among all categories.

Live Interactive Dashboard

Project Details

This machine learning model is built for predicting the price of homes in bengaluru . We did data preprocessing – Handled NA values, Feature Engineering – created new columns ‘bhk’ and sq. feet per price, converted sq. feet few string value into float, dimensionality reduction – reduced number of location, outlier removal using std deviation and mean,used one hot encoding for location, built mode using linear regression, used k fold cross validation to measure the accuracy of linear regression model,gridsearchcv. Python Numpy and Pandas for data cleaning Matplotlib for data visualization Sklearn for model building.

Project Details

- Project Objective

This machine learning model is built for predicting the news whether it is real or fake using logistic regression.

- Task

1. Data preprocessing
– Handled NA values.
– Used Stopword to remove the words which is not adding the value in sentence.
– Used Stemming to reduced the word into its root word.

2. Feature Extraction - Vectorizer to convert the text data into numerical data.
3. checked the accuracy of model using accuracy score.

Project Details

• Project Objective
This machine learning model is built for clustering of different customers who has high purchase score and which has low purchase score the using K means clustering.
• Task
1. Data preprocessing – Handled NA values.
2. Finding WCSS – within clusters sum of squares
3. K – means clustering model

Project Details

Project Objective This machine learning model is built for predicting whether patient is diabetic or not using vector support classifier.

Task 1.Data preprocessing – Handled NA values. 2.Data Standardization

Library Used Python, Numpy and Pandas, support vector classifier, Sklearn for model building.