Anupam is a passionate data enthusiast who loves furnishing insights and analytics to achieve opportunity identification, process reengineering and corporate growth. He recently attained his master’s degree in Business Analytics and has worked for over 2+ years on several analytics projects encompassing compelling new data sets, data models and use of statistical and visualization tools to elicit business insights. Anupam loves to slice and dice data using his own methods and you can rely on him to ask questions, connect the dots, and uncover opportunities that lie hidden within, with the ultimate goal of realizing the data’s full potential. He firmly believes that ‘knowledge is power’ and has a natural curiosity to learn new things every day. With his creativity, focus and optimism, he strives to the best of his abilities to achieve his targets. He looks forward to working at the intersection of data analytics and strategic decision making.
Anupam’s Key Strengths include:
Data Analytics Pipeline: Hypothesis Testing, Exploratory data analysis, Feature engineering, Predictive Modelling, Reporting and Data visualization.
Data Science Techniques: Machine Learning, Regression, Optimization, Time Series Analysis, SVM, Clustering, CART, KNN, Random Forest, ARIMA, PCA, Variable Selection, Cross validation, Natural Language Processing (NLP).
Tools: Python, Oracle-PL/SQL, Tableau, SAP Business Objects, SAP Business Objects Data Services-ETL (Extract, Transform, Load), SAS, R.
-
Experience
SAP
Data Science Consultant, Capstone Project
• Created NLP based predictive models for the client to forecast hourly wage of the job seeker and capture top talents with relevant skills. Planning and Execution:
• Evaluated performance metrics, reviewed and brainstormed with internal stakeholders to create and execute 4 different model roadmaps.
• Identified the pitfalls of different approaches and developed a framework to implement a ~10% more accurate hybrid classifier. Key Accomplishments:
• Conceptualized end-to-end solution to extract the skills and predict wages from job descriptions, saving ~$15k of the client’s budget.
• Recommended the best strategy to estimate the wages for a job title that can save the data scientists an average of 2 hours per day. Methodologies/Technologies used:
• Natural Language processing (NLP), Random Forest Regressor & Classifier, Naïve Bayes Classifier, Python (pandas, sklearn, matplotlib).
TOUGHBUILT INC Los Angeles, CA, USA Business Analyst Intern, Customer Relationship Management June 2019-Aug 2019 • Analyzed the customers and their response to the beta release of an android based mobile application, optimizing the app by 25%. Planning and Execution:
• Leveraged customer behavioral data of a mobile application through NLP to measure user engagement and eliminate app defects.
• Performed A/B testing for a twofold increase in user traffic, optimized the conversion rate and increased the revenue per visitor to $5. Key Accomplishments:
• Led the design of minimum viable product prototype to establish the Product-Market Fit (PMF), reducing the risk of failure by 10%.
• Built a predictive customer lifetime value (LTV) model to boost the degree of retention of highly targeted customers by 18%. Methodologies/Technologies used:
• Sentiment Analysis, A/B Testing, K-Means Clustering, Google Analytics, Python (numpy, pandas, sklearn), Tableau.
Cross-functional Work:
• Conducted product presentations and interacted with diverse beta testers to get their feedback on product features and enhancements.
TATA CONSULTANCY SERVICES Mumbai, MH, India Data Analyst, Financial Reporting Team October 2016-July 2018 • Developed analytical dashboards of transaction history, stages of loan application and fraud case identifier in a finance firm, saving $50k. Planning and Execution:
• Built 4 databases, ETL pipelines,18 batch jobs and 28 dashboards to enhance the overall system functionality and traceback applications.
• Created database objects and queries in PL/SQL to fulfill ad hoc customer needs, achieving a customer satisfaction index of 93.5%. Key Accomplishments:
• Devised a Non-Profitable Asset (NPA) system for likelihood of a new application to be an NPA, reducing the loan sanctioning risk by 10%.
• Enabled 20% approvals within 48 hrs. from application creation time by automating the queue movement via online dashboards. Methodologies/Technologies Used:
• Logistic Regression, PL/SQL (ad-hoc querying, views, mviews), SAP Business Objects (BO), SAP Data Services (BODS), Agile, SDLC. Cross functional Work:
• Presented the achievements of the team to the client and won the inter-team competition, thereby awarded the ‘Production Pillar’.
-
Projects
Github: https://github.com/anupam15394?tab=repositories
Tableau: https://public.tableau.com/profile/anupam.sinha3579#!/