Data Scientist

RAVI KUMAR SINHA

Atlanta, GA *******@*******.***.*** +1-404-***-****

https://ravikumarsinha234.github.io https://www.linkedin.com/in/ravikrsinha/ https://github.com/ravikumarsinha234 EDUCATION

Georgia State University, Atlanta, Georgia Aug 2022 – Present Master of Science in Analytics, Data Science and Analytics CGPA: 3.97/4.0 National Institute of Technology, Nagaland, India Aug 2016 – Aug 2020 Bachelor of Technology, Electronics and Instrumentation Engineering CGPA: 9.74/10

[Academic Achievement: Institute Rank 1]

WORK EXPERIENCE

GEORGIA STATE UNIVERSITY, Atlanta, US Researcher Aug 2022 – Present Data Scientist Researcher @ Evidence Based CyberSecurity Research Group April 2024 – Present

• Engineered AI solution using Google BERT-based classifier (open-source) funded by U.S. Department of Homeland Security to detect financial fraud and identity theft through illicit transactions on Telegram. Achieving over 90% accuracy and resulting in reported savings of over $10 million.

• Tech Stack: Python (Selenium, Beautiful Soup, GeoPy), PyTorch, R, Keras, Transformer Models, MS Excel Researcher @ Data Mining Lab Aug 2022 –May 2023

● Collaborated with Prof. Rafal Angryk on NASA/NSF-funded space weather prediction research, utilizing the SWAN-SF dataset. Applied high-dimensional data optimization techniques (ANNOY, KNN) and time series analysis on solar flare data.

● Tech Stack: Python (Scikit-Learn, Numpy, Pandas, Matplotlib, TsLearn) AVISO AI, Hyderabad, India Software Engineer / Data Engineer Jan 2022 – Jun 2022 Backend Python Developer, Sales & Revenue Intelligence Project Tech stack: Python, Django, MongoDB, SFDC, AWS

● Development of new Customer Enhancement Features which played a key role in customers retention.

● Worked on Optimization and bug fixes in the existing product. CAPGEMINI TECHNOLOGY SERVICES INDIA LTD, Mumbai, India Software Engineer (Big Data Practice) Client: Morgan Stanley Tech Stack: Scala, Spark, Hadoop, Hive, Python, PySpark Jan 2021 – Jan 2022

● Migrated Java, DB2 based Anti-Money Laundering based transaction monitoring system to Scala-Spark based architecture which made the data processing speed 30% faster.

● Implemented a High-Risk Jurisdiction Regulatory Scenario in the transaction monitoring system via algorithms written in Scala and running as Spark process. This helped analysts from the Financial Crime team to track the potential money laundering. CHENNAI MATHEMATICAL INSTITUTE, Chennai, India (32 selections from India) May 2019 – Jun 2019 Summer School on Mathematical Finance Tech Stack: R, Linux

● Studied mathematical finance topics, implemented ARIMA on stock returns, and used Random Forest to reduce error by 15%.

● Analyzed 15 years of NSE India stocks data to present a case study on the Impact of Assembly Elections on specific stock prices. INDIAN INSTITUTE OF TECHNOLOGY, New Delhi, India Fellowship under Prof. B.K. Panigrahi May 2018 – July 2018

● Generated and analyzed power system disturbances using wavelet transformation in MATLAB, extracting statistical features, and predicting disturbances with AI algorithms for optimal performance comparison. ACADEMIC PROJECTS

Heart Disease Classification on Cleveland UCI Data July 2022 – Sept 2022

● Performed Exploratory Data Analysis, created visualization with attributes to find patterns, experimented with different ML algorithms and found Logistic Regression and Random Forest to be best model. Used Hyperparameter tuning to enhance accuracy to 88 %. Tech Stack: Python (SciKit-Learn, Pandas, Numpy, Matplotlib, Seaborn) AutoML on the Compressive Strength of different Concrete Mixes Sep 2022 – Oct 2023

● Used PyCaret library to find the best 6 algorithms via AutoML. Tuned the hyperparameters for the selected models. Visualization of Feature Importance and Residual Graphs.

● Evaluated the models on the various evaluation metrics. Choose the most suitable model for deployment. CERTIFICATIONS

• Google Advanced Data Analytics Certification (2024) Microsoft certified Azure Data Engineer Associate (2024) TECHNICAL SKILLS

● General Skills: Machine Learning, Deep Learning, Natural Language Processing, Data Visualization, Statistical Analytics, Distributed Computing, Advanced Analytics, Advanced Excel, Backend Engineering, Problem-Solving Skills, Agile

● Programming Languages: Python, SQL, Scala, R, C

● Frameworks/Libraries: NumPy, Pandas, SciPy, Sci-kit Learn, Keras, Pytorch, Tensorflow, Spark, Hadoop, Hive, Selenium, Talend, MapReduce, HuggingFace

● Web Tech/Database/Tools: AWS, Oracle cloud, Jupyter, Postgres, MongoDB, Django, Flask, MySQL, MATLAB, Tableau, Power BI, Git, Jira, HTML, CSS

● Business Intelligence Tools: Tableau, Power BI

Contact this candidate