S Singh Email and Phone Number

Text Mining for Classification : Objective is to classify the text records which are logged by users of a large application in to different classes and route them to respective teams to act on requests. Users log their requests related to enquiries, Issues they face and any clarification they needed. Also third party log the requests related to claims, clarifications etc. Currently classification is being done manually by domain experts.Naïve Bayes Machine Learning algorithm: Considered the data in billing division, defined and standardized the classes definitions. Got training data set coded manually with the standardized definitions. Divided the data set in to training and validation sets in 60: 40 ratio respectively. Data pre- processing techniques included– removing stop words, extra white spaces, numbers, stemming the words. Tokenization was done using DocumentTermMatrix and sparse matrix was built. Built the Naïve Bayes model and validated the model using validation set. Accuracy of the model was improved by changing the Laplace constant.Cost Effective Analysis Using customer’s data identify opportunities and optimize conversion and revenue/profitability within Verizon’s financial business unit. Analyzing customer paths across all channels - Digital / Contact Centers / Retail to help improve the overall customer experience and business outcomes. Managing daily, weekly, and monthly report execution and distribution, Highlighting Key Performance Indicators, Partnering with Finance, Marketing and other cross functional teams in Verizon to support business initiatives

App Recommender System: Developed a personalized recommender system using recommender algorithms (collaborative filtering, low rank matrix factorization) that recommended best apps to a user based on similar user profiles. The recommendations enabled users to engage better and helped improving the overall user retention rates at appleSales Forecasting: Forecasted sales and improved accuracy by 10-20% by implementing advanced forecasting algorithms that were effective in detecting seasonality and trends in the patterns in addition to incorporating exogenous covariates. Increased accuracy helped business plan better with respect to budgeting and sales and operations planningAnomaly Detection: Created interactive dashboard suite that illustrated outlier characteristics across several sales-related dimensions and overall impact of outlier imputation in R (Shiny).Used iterative outlier detection and imputation algorithm using multiple density-based clustering techniques (DBSCAN, kernel density estimation)Cross Sell and Upsell Opportunity Analysis: Implemented market basket algorithms from transactional data, which helped identify items used/purchased together frequently. Discovering frequent item sets helped unearth cross sell and upselling opportunities and led to better pricing, bundling and promotion strategies for sales and marketing teams

Played a key role in developing and maintaining statistical and machine learning models that mine, analyze and turn groupon customer and sales data into insights that helped groupon make strategic decisions that led to growth in their user base and revenueCustomer Participation Analysis: Built relational databases in SQL server of several flat files of partner information from several large (5-10 GB) flat files in Python. Used logistics regression and random forests models in R/Python to predict the likelihood of customer participation in various marketing programs. Designed and developed visualizations and dashboards in R /Tableau that surfaced the primary factors that drove program participation and identified the best targets for future targeted marketing effortsCustomer Life Time Value Analysis: Projected customer lifetime values based on historic customer usage and churn rates using survival models. Understanding customer lifetime values helped business to establish strategies to selectively attract customers who tend to be more profitable for groupon. It also helped business to establish appropriate marketing strategies based on customer valuesCustomer Segmentation: Developed 11 customer segments using unsupervised learning techniques like KMeans and Gaussian mixture models. The clusters helped business simplify complex patterns to manageable set of 11 patterns that helped set strategic and tactical objectives pertaining to customer retention, acquisition and spend Price Optimization and Revenue management: Measured the price elasticity for products that experienced price cuts and promotions using regression methods; based on the elasticity, apple made selective and cautious price cuts for certain licensing categories

Played key role in developing and deploying DFAST Stress Test models across several bank portfolios. Provided architectural leadership on several high priority initiatives including account prioritization, account prospecting, and opportunity scoring. Drove the creation of comprehensive datasets encompassing user profiles and behaviors, and incorporating a wide variety of signals and data types.Forecasting Loan balance: Forecasted bank-wide loan balances under normal and stressed macroeconomic scenarios using R. Performed variable reduction using the stepwise, lasso, and elastic net algorithms and tuned the models for accuracy using cross validation and grid search techniques.Top down Models (Commercial Real Estate): Automated the scraping and cleaning of data from various data sources in R and Python. Developed Banks’s loss forecasting process using relevant forecasting and regression algorithms in R.  The projected losses under stress conditions helped bank reserve enough funds per DFAST policies

Policy Payment Default Prediction: Built classification models using several features related to customer demographics, macroeconomic dynamics, historic payment behavior, type and size of insurance policy, credit scores and loan to value ratios and with accuracy of 95% accuracy the model predicted the likelihood of default under various stressed conditions.Customer Trial Repeat Analysis: Designed and deployed real time Tableau dashboards that identified policies which are most/least liked by the customers using key performance metrics that aided the company for better rationalization of their product offeringsCustomer Segmentation: Clustered the customers based on demographics, health attributes, policy inclinations using hierarchical clustering models and identified strategies for each of the clusters to better optimize retention, marketing and product offering strategies

Marketing Campaign Measurement: Built executive dashboards in Tableau that measured changes in customer behavior post campaign launch; the ROI measurements helped company to strategically select the effective campaigns Credit Risk Scorecards: Built credit risk scorecards and marketing response models using SQL and SAS. Evangelized the complex technical analysis into easily digestible reports for top executives in the company. Developed several interactive dashboards in Tableau to visualize nearly 2 Terabytes of credit data by designing a scalable data cube structure.Others Analyzed large datasets to provide strategic direction to the company. Performed quantitative analysis of ad sales trends to recommend pricing decisions. Conducted cost and benefit analysis on new ideas. Scrutinized and tracked customer behavior to identify trends and unmet needs. Developed statistical models to forecast inventory and procurement cycles. Assisted in developing internal tools for data analysis. Designed scalable processes to collect, manipulate, present, and analyze large datasets in production ready environment, using Akamai's big data platform Achieved a broad spectrum of end results putting into action the ability to find, and interpret rich data sources, merge data sources together, ensure consistency of data-sets, create visualizations to aid in understanding data, build mathematical models using the data, present and communicate the data insights/findings to specialists and scientists in their team Implemented full lifecycle in Data Modeler/Data Analyst, Data warehouses and DataMart’s with Star Schemas, Snowflake Schemas, and SCD& Dimensional Modeling Erwin. Performed data mining on data using very complex SQL queries and discovered pattern and used extensive SQL for data profiling/analysis to provide guidance in building the data model

 Participated in JAD sessions, gathered information from Business Analysts, end users and other stakeholders to determine the requirements Designed the Data Warehouse and MDM hub Conceptual, Logical and Physical data models Used Normalization methods up to 3NF and De-normalization techniques for effective performance in OLTP and OLAP systems. Generated DDL scripts using Forward Engineering technique to create objects and deploy them into the database Worked with SME's and other stakeholders to determine the requirements to identify Entities and Attributes to build Conceptual, Logical and Physical data Models.  Used Star Schema methodologies in building and designing the logical data model into Dimensional Models extensively. Developed Star and Snowflake schemas based dimensional model to develop the data warehouse. Designed Context Flow Diagrams, Structure Chart and ER- diagrams