Home

Govin Muthukrishnan - Sr Data Scientist

[email protected]

Location: Jersey City, New Jersey, USA

Relocation: yes

Visa: USC

Govin Muthukrishnan 732-387-5744 [email protected] SUMMARY Over 7+ years of experience in the financial industry in several functions including Data Science, Data Analytics, Quantitative Finance, Machine Learning, Natural Language Processing, Statistics and Data Visualization. Led and managed team involvement through the entire Data Science project life cycle including Business Requirement Understanding, Data Sourcing, Data Wrangling, Data Pre-processing, Exploratory Data Analysis (EDA), Model Development, Model Validation and Model Implementation Skilled in using statistical and machine learning techniques to extract insights and drive business decisions. Strong programming background in Python and R to implement data analytics, data visualization, model implementation and automation solutions. Successfully developed predictive models by leveraging big data technologies and delivered efficient and measurable results. Highly skilled in applying supervised and unsupervised Machine Learning techniques SVM, Decision Trees, Random Forests, LDA, XG Boost, K-Nearest Neighbors, Clustering, Linear and Logistic Regressions. Extensive experience with Data Preprocessing involving Data Cleaning, Data Transformation, Data Imputation, Outlier Detection and Residual Analysis of both structured and unstructured datasets. Proficient with various methods of Data Sampling Stratified, Cluster, Multistage, Systematic and highly skilled at developing solutions to address issues with Data Quality and Data Security Expert in Statistical Analysis both Descriptive Statistics and Inferential Statistics including Univariate & Multivariate Exploratory Data Analysis (EDA), Hypothesis Testing, Regression Methods, A/B Testing, Causal Analysis, Prescriptive Analysis and Predictive Analysis Graduated from UC Berkeley with a Master of Information and Data Science, gaining expertise in data mining, predictive modeling, statistical inference, and programming, subsequently applying the skills to successfully solve complex business problems and create data-driven decisions. Skilled in Business Intelligence using Tableau to design visualizations and charts, subsequently, presenting and publishing interactive dashboards to stakeholders. Efficiently managed and streamlines Machine Learning projects using MLFlow Experience using various analytic tooling platforms to program, test, analyze and validate including Anaconda, Jupyter Notebook, PyCharm, R, MATLAB, and Microsoft Excel Involved with the SDLC lifecycle using optimization practices like Agile development (Scrum, Kanban) and DevOps (and CI/CD) technologies like Jenkins, Docker, Google Cloud Platforms (GCP) and Microsoft Azure Well versed with best practices of Python development (PEP-8) and use of Data Science and Analytics libraries Pandas, NumPy, SciPy, Scikit-Learn, Matplotlib, Seaborn, Hugging Face, Scrapy, BeautifulSoup, NLTK, Gensim, Word2Vec, PyTorch, TensorFlow, etc Strong experience with SQL in developing queries to source data from enterprise firm-wide data sources as well as the execution of model implementation (including assumptions, overlays, and calculations) Experience with convoluted applications of Machine Learning like Sentiment Analysis, Natural Language Processing (NLP) for Text Analytics, Topic Modeling, and use of NLP techniques like Bag-of-Words (BoW) and N-Gram Algorithms Excellent communication skills including presentations with stakeholders, documentation, networking, and meaningful coordination between business and technical teams. Passionate about leveraging data to create meaningful impact and solve complex business challenges. Strong learner, great interpersonal skills, team-player, and an avid problem solver. EDUCATION Master of Information & Data Science Aug 2021 University of California, Berkeley Bachelor of Science in Electrical and Computer Engineering May 2017 Rutgers University, New Brunswick Honors Cum Laude SKILLS Data Science: Statistical Modeling, Machine Learning, Natural Language Processing, Python Tooling (Pandas, Scikit-learn, NumPy, SciPy,) Data Tools: Tableau, JavaScript, Splunk Languages: Python, SQL, R, Bash, Perl, MATLAB DevOps: Google Cloud Platform (GCP), Docker, Agile SDLC, GitHub, Jenkins, Ansible, AWS S3, IDEs Jupyter, PyCharm, Linux Cryptography: PKI, OpenSSL, Certificate Lifecycle Management, HashiCorp Vault, Thales KeySecure CAREER EXPERIENCE Egrove Systems, East Brunswick NJ May 2023 Present Data Scientist / System Architect / Business Development Oversaw a variety of projects at Egrove Systems, including Data Science, System Architecture, and Government Contracting Business Development, while fostering innovation, enhancing productivity, and bringing in more revenue. Led five ad hoc data science projects for external clients, such as image recognition and text extraction projects, using advanced machine learning methods to create custom solutions that met client goals. Analyzed product subscription data and put data-driven strategies in place to improve customer retention rates. Key performance indicators (KPIs) were established, and insights were used to guide targeted marketing efforts, which led to a 25% rise in customer engagement. Developed custom machine learning models and algorithms to look at big datasets and find actionable insights. These models and algorithms helped with strategic decision-making for both internal operations and client projects, which led to a 30% increase in operational efficiency and business performance. Collaborated closely with cross-functional teams to seamlessly integrate data science solutions into existing systems and workflows, ensuring smooth implementation and maximizing the value provided to clients. Led the redesign of the Elite Site Optimizer product's architecture, which included all parts of its development, from the backend Python code to the front-end design, making sure that it met the needs of the business along with speed, scalability, and security. Provided technical leadership and mentoring to development teams, assisting them with technical problem-solving and promoting a culture of innovation and continuous improvement within the company. Through extensive market research and networking, Identified and pursued over 20 lucrative government contracting opportunities, leading to a 40% increase in successful contract acquisitions and revenue growth. Crafted convincing proposals that met the needs of government agencies by including thorough technical solutions, accurate cost estimates, and attainable timelines. This made the company more competitive and increased its success rate in getting government contracts. Participated in 10+ industry conferences, networking events, and government contracting forums to stay up to date on industry trends, spot new possibilities, and grow the company's presence and influence in the government contracting sector. Bank of America, Jersey City NJ Mar 2022 May 2023 Assistant Vice President Data Scientist Quantitative finance analysis in Enterprise Risk Analytics (ERA) assessment and development of cross-business, holistic analytical models, and tooling Responsible for supporting the calculation of asset level balance sheet for Financed Emissions to achieve the bank s goal of Net-zero greenhouse gas emissions by 2050 Develop regression models as well as models using ensemble machine learning techniques (Random Forest, XGBoost) to predict the fuel consumption of residential homes, achieving a net margin error of 17% Create the Proof of Concept (POC) to implement the mortgage model on Bank of America s residential mortgage loan portfolio to predict energy estimates and subsequently calculate the bank s exposure in financed emissions Collaborate with Line of Businesses (LOBs) to present findings, discuss feedback and implement the data-driven decisions to subsequent model runs applying exclusions, filters, calculation changes and conversions Design charts and visualizations using Tableau for presentations with stakeholders and publish interactive Tableau dashboards for end-users Analyze, review and provide solutions to address data quality issues of sourced portfolio data from third-party vendors and subsequently apply asset-class specific data pre-processing Unify a singular dataset for model run calculations by reconciling population, exposure, and intensity values between sourced and proprietary data sets Review and maintain model documentation for BofA s internal Model Resource Management review Automated recurring SQL queries using internal CI/CD pipeline to efficiently mitigate risk of error AT&T, Middletown NJ Sep 2021 Mar 2022 Data Scientist Data Science consultant in Field Operations Technology dedicated division to maintain and improve the technological capabilities and services for field operations Integrated Text Analytics tooling to parse information from technician manual PDFs and workbooks Designed a document search engine using Elasticsearch for extracted and pre-processed technical data Used HuggingFace libraries and Natural Language Processing (NLP) transformers, created a Chatbot to support a technician-facing question-answering interface Partnered with product teams to identify enhancement opportunities using Artificial Intelligence (AI) as well as predictive and prescriptive modeling Morgan Stanley, New York NY Jan 2019 Aug 2021 Cryptographic Services Engineer Fulfilled specified scope in providing company-wide strategies and solutions for security, comprising data protection, secrets management, and authentication through cryptography. Engineered the health monitoring framework for Crypto products that assesses system connectivity, task performance, resource management and overall state of readiness-for-business (RFB) Built a Splunk dashboard that visualized all identified vulnerabilities and alerted the team about issues, necessary resolutions, and possible outage scenarios Pioneered the resource capacity planning system for Crypto Services to forecast system usages allowing to plan for additional capacity in advance, achieved by: o Analyzing both product and infrastructure data to identify patterns and trends o Establishing relationships among crypto products as well as external products and services Presented Crypto solutions to customers other application and service teams in the firm by showcasing product features and proposed integration methods; subsequently assisted customers as a Crpyto liaison for implementation Generated routine monthly reports for the Public Key Infrastructure with detailed metrics of certificate creation requests, number of certs processed manually vs using auto-tooling, major issues, failures, and anomalies Created quantifiable metrics to assess the performance of firm s proprietary secrets management system Secure Credential Vault Developed automation scripts in Python to assist and support repetitive manual operational tasks Optimized software delivery end-to-end processes by integrating Agile tools reducing the time from development to production by 50% Keywords: continuous integration continuous deployment artificial intelligence sthree active directory rlang information technology New Jersey New York