DISHITA JAIN

857-***-**** ad1m0g@r.postjobfree.com linkedin.com/in/dishitajain02

EDUCATION

Northeastern University, Boston, MA. Expected May 2024 Degree: Master of Science in Data Analytics Engineering Shri Vaishnav Vidyapeeth Vishwavidyalaya, Indore, India May 2022 Degree: Bachelor of Technology in Computer Science with specialization in Big Data Analytics (In collaboration with IBM) SKILLS

Programming Languages: Python (NumPy, Pandas, Scikit-learn, Matplotlib, Computer Vision), SQL, R Business Intelligence: Qlik Sense, Advanced MS-Excel, SAS, Spark, Tableau, Power BI Data science/analytics: ETL, MySQL, NoSQL, SQL Server, TensorFlow, Data warehousing & modeling Cloud Technologies: AWS, Azure

RELEVANT EXPERIENCE

Allsoft Solutions and Services Pvt. Ltd (Partner-IBM) Machine Learning (ML) Intern Jan 2022 - July 2022

• Developed facial recognition system for emotion detection, achieving 85% accuracy on test data by implementing deep learning model

(CNNs) using TensorFlow to analyze and preprocess 10,000+ images.

• Created and maintained ETL pipelines using Apache Airflow, ensuring efficient data processing and integration across different sources.

• Utilized Git for version control and collaboration, ensuring smooth coordination among team members and efficient project management.

The Sparks Foundation Data Science and Business Analytics Intern Nov 2020 - Dec 2020

• Utilized SQL and NoSQL queries to clean and transform data from 20+ sources, resulting in the development of Power BI dashboards that simplified complex KPIs for investors, leading to a 25% increase in clientele base.

• Conducted statistical analyses on data sets to identify patterns, relationships, outliers, and other anomalies, providing key insights that drove strategic decision-making.

• Analyzed business and market trends, idenSfying improvement opportuniSes, and delivered presentaSons to key stakeholders including execuSves and management teams.

ACADEMIC PROJECTS

Medicare Provider Fraud Detection Feb 2023 - May 2023

• Conducted exploratory data analysis on a large dataset, uSlizing SQL to clean, preprocess, and handle missing values and outliers, ensuring data readiness for machine learning modeling.

• Created an ensemble machine learning model by integraSng LogisSc Regression, Decision Tree, and Random Forest Classifier algorithms to idenSfy healthcare fraud in Medicare providers, achieving an impressive accuracy rate of 93% in detecSng fraudulent claims.

• Implemented real-Sme monitoring and alerSng systems to proacSvely detect and prevent potenSal fraudulent acSviSes. Restaurant Management System Sept 2022 - Dec 2022

• Collaborated to work on a real-world problem and developed an ETL process for a local restaurant to transform and load data into MySQL database using python.

• Conducted ad-hoc analysis to investigate customer consumption and shaped a series of recommendations that improved system integration, resulting in a 25% increase in customer retention rates.

• Created dashboards on Tableau to analyze key business metrics, which helped the stakeholders take profitable business decisions. Human Activity Recognition (Time Series) Oct 2022 - Nov 2022

• Developed an algorithm to detect activity of humans using accelerometer data for 15 different subjects.

• Used time-series analysis techniques like permutation entropy and complexity to get an accuracy of 93.3%.

• Employed feature engineering to extract meaningful insights from raw accelerometer data, enhancing the algorithm's performance.

LEADERSHIP AND CERTIFICATIONS

• Industrial Training with IBM in Artificial Intelligence (AI).

• Google Analytics Certification.

• Excelled in competitive Table-Tennis for 8 years, accomplishments include team captain and first place in the state level tournament.

Contact this candidate