Shrishti Jain

Shrishti Jain -|-| LinkedIn | Github | Leetcode Experience Ernst & Young Aug. 2024 – Present Senior Analyst • Developed and deployed 10+ interactive dashboards using Power BI and Excel for 2 client teams, enabling real-time KPI tracking, proactive risk identification, and ensuring data accuracy, quality, and security. • Automated routine reporting and data processing workflows using Power Automate and VBA macros • Designed and built internal tools to automate data extraction and processing using Python and OpenAI API accelerating data collection and analysis for internal reporting. • Collaborated with cross-functional teams and clients to gather and understand business requirements for data-driven decision-making. Defence Research and Development Organisation(DRDO)-SAG July 2023 – Sept 2023 Machine Learning Intern • Designed a large-scale dataset for Differential Cryptanalysis, optimizing it for deep learning model development and performance analysis. • Models Used: ResNet, AlexNet Triotree Technologies Pvt. Ltd. Aug. 2022 – Sept. 2022 Application Development Intern • Worked under the development team on a Hospital Appointment Booking App using React-Native. Skills Languages: Python, C++, Java, SQL Data Analysis & Visualisation: MS Excel, Power BI, Tableau, Power Automate Data Engineering: ETL Pipelines, Data Warehousing, Data Modeling, PySpark, Macros, VBA Databases: MySQL Data Science: Data Analysis (NumPy, Pandas), Data Visualization (Matplotlib, Seaborn), Machine Learning, Deep Learning Others: Git, Github, Linux Projects Heart Disease Detection using ECG | Github | Deep learning, LSTM, GRU • • • Utilised "ECG Images dataset of Cardiac Patients" to analyse ECG data and detect patterns associated with myocardial infarction and other cardiac abnormalities. Preprocessed and Digitised the ECG data, using Binarization and contour generation techniques, to a 1D signal. Developed an ensemble model using LSTM and GRU architectures, achieving an 87% accuracy. Cryptanalysis using ResNet | Deep learning, ResNet architecture, Cryptanalysis • Utilized a ResNet model to evaluate the effectiveness of the Speck 32/64 cipher by elucidating potential weaknesses in the cryptographic algorithm when subjected to advanced deep learning techniques. . Depression Detection System | Github | Deep Learning, Machine Learning • A multi-modal model was created to evaluate depression symptoms in users, leveraging facial expression analysis (CNN on CK+48 dataset with 89% accuracy), speech analysis (CNN on DAIC-WOZ dataset with 70.21% accuracy), and motion activity analysis (KNN, XgBoost, and Random Forest models achieving 70% accuracy) . Education Bharati Vidyapeeth’s College of Engineering New Delhi B.Tech, Computer Science and Engineering CGPA: 9.1 2020 – 2024 St Andrews Scots Sr. Sec. School New Delhi 12th Percentage:94.4% 10th Percentage:86.4% 2019 - – 2018 Achievements • • • • • • • Awarded as Emerging Extraordinaire at EY(Certificate) Technovation 3.0 (Secured 2nd place among 200 teams)(Certificate) WIEHACK 4.0 (Secured 3rd position among 2k+ teams)(Certificate) 1556th rank at Code Jam to I/O for Women 2022 Qualified for Round 1 of Google Code Jam 2022 NEXAS (Hackathon) (Finalist) Talentsprint WE (Among top 200 from 28k participants)