Cleaned and pre-processed large datasets (95% reduction in data errors) to ensure high-quality data for analysis
Utilized statistical tools and software (Python, SQL, Excel) to analyze datasets with up to 100,000 records and
extracted actionable insights (resulting in 25% increase in process efficiency)
Created visualizations and dashboards using tool like Power BI
Assisted in developing predictive models (boosting
model accuracy by 15%).
Education
B.TECH - Computer Science
Punjab Technical University
Mohali, Punjab
08.2019 - 07.2023
XII - undefined
Skills
Python
Libraries: pandas, matplotlib, ggplot2
Scikit-learn, NumPy
Power Bi
Tools: DAX, API, Power Query
Analytics
Artificial Intelligence
Machine Learning, Deep Learning
ML
Regression, Classification, Clustering
Feature Engineering, Model Evaluation
SQL
Joins, Indexes, Queries
Normalization, Subqueries
MS Excel
Tools: Pivot Table, Data Analysis
VBA, Formulas
Soft Skills
Team Player, Leadership
Analytical
Projects
Data Profiling
Report Preparation
Database Programming and SQL
Business Performance Analysis
Data Collection Management
Structured Query Language (SQL)
Data Integrity Validation
Data and Analytics
Jupyter Notebook
Logistic Regression
Microsoft Power BI
Business Tracking
Business Intelligence Testing
Model Data
BI Tool and System Design
Extraction Transformation and Loading (ETL)
Accomplishments
Certification in Python (Machine Learning) from Solitaire Infosys (Mohali), focusing on practical implementations and real-
world applications of Python and Machine Learning
Certification in Data Analyst from Simplilearn, covering data analysis techniques, data visualization, and statistical analysis
Certification in Data Analyst From IBM, mastering advanced data analysis tools and methodologies, including IBM's
proprietary technologies and frameworks.
Additional Information
Developed a robust movie recommendation system using advanced machine learning algorithms in Python, resulting in a 20% increase in recommendation accuracy. Leveraged powerful Python libraries, including NumPy and Pandas, for efficient data manipulation and preprocessing of over 100,000 user ratings and movie features. Employed collaborative filtering techniques, analyzing user preferences to deliver personalized movie recommendations with a precision score of 0.85. Utilized comprehensive data from user ratings and detailed movie features to construct a highly predictive model, achieving an RMSE of 0.90. FOOD DELIVERY END TO END MACHINE LEARNING PIPELINE Collected and pre-processed order, customer, and delivery data, handling over 100,000 data points to ensure accuracy and consistency. Engineered features to enhance model performance, resulting in a 20% improvement in prediction accuracy. Trained machine learning models and deployed them using APIs for real-time predictions, reducing latency by 30%. Conducted comprehensive testing and validation, identifying and classifying emotional states across diverse datasets.
Work Preference
Work Type
Full Time
Important To Me
Career advancementWork-life balanceWork from home option