We provide IT Staff Augmentation Services!

Sr. Data Scientist Resume

MI

SUMMARY:

  • Having 9+ years of Advanced Analytics and Business Intelligence/Data Warehousing (BI/DWH), Predictive Statistical Modelling experience with focus on quality solutions. Has research expertise in Confidential, Big Data Analytics, Numerical and Quantitative Methods for Finance and High Performance Computing (HPC).
  • Proficient in implementing various machine learning and statistical methods for Forecasting /Predictive Analytics, segmentation, and Optimization. Regression models, PCA, time series analysis (AR, ARMA, ARIMA), Structured and Unstructured data, Big data.
  • Data mining experience with R - 3.3(glm, rpart, GenSA, GA, lokerns, mgcv, mars), SAS-9, Matlab-R2016b and Python(SciPy, scikit-learn, NumPy, pandas, tensorflow).
  • Prediction/Forecasting for finance instruments and time series analysis.
  • Siebel 8 CRM Consultant: Siebel Enterprise Application Integration, Enterprise Integration Manager, Order Management, Universal Customer Master.
  • Experience with Data Analytics, Advanced Reporting, Business Intelligence reporting.
  • Experience in visualization: Jupyter Notebook, Oracle BI, IBM Cognos, MS Excel, Tableau, R, Google Charts.
  • Team leader and player with organizational, analytical problem solving and leadership capabilities to attain organizational objectives.
  • Segmenting customers with respect to business objective such as Demographic & Geographic Segmentation, Behavioral Segmentation
  • Experience in Change Management, Baselining and Version Control tools like GitHub, IBM CMVC, IBM Rational ClearCase.
  • Optimization techniques using Multivariate & Operations Research methods.
  • Data cleansing/pre-processing and data reduction methods.
  • Data Management (ETL) with IBM DataStage v7.5/v8, Informatica PowerCenter v9.
  • Domain Knowledge: Retail, Finance/Banking, Wireless Telecom, Information Technology

TECHNICAL SKILLS:

Programming Expertise: R-Language v3.3, SAS Base v9, Python v2.7/v3 (TensorFlow v0.8/v1.0, scikit-learn), Java, Scala, SQL(Oracle 10g/Teradata/MYSQL/DB2/SAS SQL), C++11 - Hybrid Node for HPC (CUDA/OpenMP/ OpenACC/ OpenMPI), C++ with OpenCV, VBA, Hadoop, Hive, Pig, Splunk Analytics, HBase.

Visualization Tools: MS Excel, Oracle BI, Tableau, IBM COGNOS 8, R, Google Chart, Hyperion BrioQuery

Method Expertise: Statistical Modeling, Data Analytics, Business Intelligence, Data Warehousing, Machine Learning and Optimization

Techniques: Regression, HMM, GLM, Decision Trees, Random Forest, Clustering (K-means, Hierarchical), Association Rules, K-Nearest Neighbors, Neural Nets, SVM, Bayesian, Linear Programming, MapReduce, Genetic Algorithm.

ETL Skills: IBM DataStage/ QualityStage v7.5/v8, INFORMATICA PowerCenter v9

Secondary Skills: Unix Admin/ Shell Scripting, MATLAB, Siebel 8 CRM, Amazon AWS, Microsoft Azure, Drupal 6 CMS with PHP

PROFESSIONAL EXPERIENCE:

Confidential, MI

Sr. Data Scientist

Responsibilities:

  • Adobe Web Analytics ClickStream data processing for Statistical modeling preprocessing.
  • Model mobile platform B2B users with conversion on various offline channels (Contact Center, Bulk Orders, EPRO/EDI)
  • Model Mobile platform users (Contacts) personal preferences.
  • Evaluation of Search by Keyword/Navigation results to Mobile user previous purchase and current cart/order products.
  • Defining the scope of the project
  • Designing the Process reusability and customization modules

Environment: Hortonworks Hadoop Cluster on Linux Environment, R, Shiny R, MS Excel, Tableau, Teradata DB. Adobe Analytics - web ClickStream data.

Confidential

Responsibilities:

  • Defining the scope of the project
  • Designing the Process reusability and customization modules
  • Identify standard Confidential datasets, use cases and test cases
  • Object recognition, object features detection
  • Preprocessing of images/video frames (resizing, blurring, orientations, color gradients, edges)
  • Preparation of the environment from scratch (Installation and maintain Python Anaconda, Tensorflow, Jupyter Notebooks)
  • Deep Convolutional Neural Net - design depth, convolutional layer filters, pooling layers, fully connected layers
  • Weight initialization for the designed layer (Xavier Initialization)
  • Implementation - training and testing with datasets
  • Generate metrics/dashboards for recall and accuracy for test cases (Visualization using Jupyter Notebooks services)
  • Documentation for High Level and low level specifications
  • Proposals for enhancements/integrations.

Environment: Python 3 (TensorFlow v1.0), Ubuntu 16.04, Jupyter Notebooks, Convolutional Neural Nets

Confidential

Stanley Steemer

Responsibilities:

  • Defining the scope of the project, reusability and cost of maintenance.
  • Analyze the available parameters for optimization methods (preferred technician, time window for specific jobs, skill sets, multiple depots location, user specific preferences, real-time events, vehicle type)
  • Analyze data from questionnaires, historical data from legacy Route optimization tool.
  • Used multiple optimization methods, Combinatorial optimizations, Genetic Algorithm, Simulated Annealing methods were used.
  • Ranking of optimum route suggestions from multiple methods.
  • Re-optimizing based on existing fast routes and user preferences to get near real-time performance.
  • Scheduling based on optimum route selected and calculate time of flight.
  • Responsible for end-to-end development life-cycle, data collection, Analysis, model building and deployments.

Environment: R language (GenSA, GA), Python 2 (SciPy, pandas), licensed route maps with

Delay/congestion information

Confidential

Responsibilities:

  • Defining the scope of the project and documenting the requirements
  • Designing the Process Flows
  • Identifying product defects and their classification.
  • Collating image datasets for various defects, positive and negative test cases
  • Generate manual Ground truths (identify classes of objects in each frame for each pixel at full resolutions of input stream) for training and testing data.
  • Implementation of the machine learning solution, training and testing with datasets.
  • Assessing the efficiency and accuracy of the solution and representation using metrics/dashboards.

Environment: Machine Learning libraries on Python(OpenCV, scikit-learn, SciPy)

Confidential

Analyst (Analytics and Information Management) / Data Scientist

Responsibilities:

  • Understand the business requirements, Provide advanced reporting for the Customers based on various BUs on an ad hoc, weekly and monthly basis.
  • Provide valuable Insights on the Coupon Redemption Performance pattern by profiling the Customers based on redemption.
  • Customer Propensity and Seasonal Sales statistical models (Base SAS and Python models) for each department. Ranking customers on these models to get targeted customers for each campaigns. (Halloween Models, Low ticket Coupon Models at Customer levels and High ticket Coupon models at Household levels). Best fit model selection using Lift, Gain and ROC plots.
  • Revaluation of the existing models and compare the Lift and Gains of the current and new evaluations.
  • Identifying the target populations from the loyal customers for Targeted Interactions based on the previous Offers/Campaigns.

Environment: Python 2 (SciPy), SAS Base 9, R-Language, Sun Solaris, ORACLE 11g, SAS SQL, MS Excel, VBA

Confidential

Analytics and Data Management

Responsibilities:

  • Provide valuable Insights on Customer Retention and Reload Bonus Campaign.
  • Module Lead at onsite (Malaysia). Task assignment to offshore team.
  • Predict Reload (recharge) Campaign redemptions.
  • Customized Plan Offers to push postpaid customers to next billing tier.
  • Maintain and action the Enterprise Data Warehouse (in SAS SPDS) data changes.
  • Understand the business requirements, Provide advanced reporting for the Customers based on various Products, on Ad-hoc, weekly and monthly basis.
  • Reporting on MVNO client usage and Reload Bonus Campaigns.

Environment: R, Python, SAS Base, IBM AIX, SAS SPDS, Shell Scripting, Crontab scheduling, MS Excel, Oracle BI, MVNO custom portal.

Confidential

Data Strategy Consult

Responsibilities:

  • Provide automation of the Migration Processes for the different portfolios of the customer.
  • Provide Detailed Design Documentation of the data migration.
  • Provide training and briefing to the team mates.
  • Understand the business requirements
  • Analyze data from Marketing Analytics Database to Design and Develop various migration plans.
  • Design the ETL jobs in IBM DataStage v8.
  • Provide details of future scheduling of weekly data migration from various systems to the Datawarehouse.

Environment: SAP ERP, Oracle 10g, TERADATA, IBM DataStage and QualityStage v8, IBM AIX.

BI/DWH Consultant

Confidential

Responsibilities:

  • Bulk provisioning of Sales Orders as per campaigns.
  • Manage Data loads between different systems.
  • Design and implement Data Flows in IBM DataStage and Informatica PowerCenter.
  • Data Integration with the other systems for Loyalty Points, Order Approval, Billing Systems, etc.
  • Designing the Process Flow for Data Integration.
  • Maintain data consistency by weekly data check jobs with business rules and mark records for scheduled deletion.

Environment: IBM DataStage v7.5, INFORMATICA PowerCenter v9, IBM AIX, Siebel 8 EAI, IBM MQ (MessageQueue), AS400

Confidential

IBM Global Account

Responsibilities:

  • Report authoring in COGNOS 8, BrioQuery as per the business requirements from the client and its partners (ad-hoc, daily, weekly reports)
  • Deliver robust single view dashboards with all the required metrics.
  • Plan aggregation levels/methods for specific views /dashboards.
  • Understand Business requirement and convert them to visual dashboards.
  • Mapping of new data fields from various databases to the Cognos Views.
  • Implement data mapping from various systems to Cognos 8.
  • Design Business Logic and aggregation layers for reporting.

Environment: IBM Cognos 8, Hyperion BrioQuery, IBM DataStage v8, IBM AIX, IBM DB2, MS Excel.

Confidential

IBM Global Account

Responsibilities:

  • Requirements gathering and documentation
  • Co-ordination and briefing with team
  • Translate abstract business requirements into detail level which can form the basis of technical designs.
  • Analyzing data from various source systems
  • Integrating multiple sources along with cleansing, profiling and loading in the required Target areas.
  • Automation and scheduling of data loads for various geographic regions
  • Weekly and daily data job run monitoring. Work on failed jobs, Root Cause Analysis on failed data jobs.
  • Plan and document changes in data schema for different databases.
  • Weekly, Daily and ad-hoc data reports as per the requirement from sales and marketing team of IBM, for all geographic regions.

Environment: IBM DataStage v7, IBM AIX, IBM DB2, SQL, MS Excel, Shell Scripts automation and scheduling.

Hire Now