- Machine Learning Engineer & Data Scientist with more than 10 years of IT experience with last 5 years in the Predictive Analytics, Machine Learning & Big Data Hadoop Technologies.
- Skilled to mine hidden patterns within large data sets (PB & TB+) of Structured, semi - structured and unstructured data, analyze the data statistically using various methodologies and tools & to develop a hypothesis model to represent the multi-dimensional & complex data using multiple algorithms to derive the data insights to predict the outcome.
- More than 5 years of experience in OLTP, OLAP & ETL end to end Enterprise Solutions as a programmer, System/Business/Data Analysts, Product Management.
Predictive Analytics: Utilize analytical tools to analyze, explore, cleanse, transform, model & predict trends & data correlations, draw appropriate conclusions and translate analytical findings into insights & Visualization.
Modeling & Machine Learning: Design and implement statistical / predictive models and cutting edge algorithms utilizing diverse sources of data to predict failure, churn rate, health score, demand, risk, price etc.
Supply Chain, ERP, ETL and Business Intelligence: In-depth knowledge of entire Supply chain processes, Enterprise data landscape involving hundreds of data sources and destinations.
Communications and Stakeholder Management: Capable of understanding complex Business problem, converting raw data into an exciting story that influences the direction of the business and communicating with diverse teams to take a project from start to finish. Collaborate with teams to coach to develop data Solutions.
SKILLS AND TOOLS:
Data wrangling: Hadoop Apache Spark, SQL, SFrame, Pig, Hive, Python, Sqoop, Flume
Statistical Analysis using Spark, Rapid miner, SAS-JMP Pro
Predictive Modelling & Machine/Deep Learning using Spark, Tensor Flow, mxnet, Graph Lab, sklearn, Stanford Core NLP, Python NLTK. Developing or enhancing the algorithms.
Data Visualization using Shiny R Server, matplotlib, ggplot2. SAP SD, MM, BW, ABAP.
Confidential, Research Triangle Park, NC
- Derived key words topics/Insights/Trends/Duplicates on unstructured data using Text Analytic algorithms.
- Developed a predictive model to estimate multiple bug attributes.
- Extracted & analyzed large Telemetry datasets to derive insights on product adoption & Usage Analytics.
- Developed Predictive modelling to derive customer health score, Cross sell and Upsell Opportunities
Data Scientist - (Technical Manager)
- Contributed towards an annual savings of over $50M by designing, developing and testing Big Data Solutions such as Factory machine breakdown prediction, Applications with IoT devices, Network outage Analysis, Inventory optimization, Predicting Shipment Delay, Recommending the best Vendor, server log file analysis.
- Extensive Programming in Hive, Pig, Python, Spark SQL, Spark ML, Graph Lab modules on data ETL, performing statistical experiments & Analysis, log file analysis & text analytics.
- Delivered Internal Training classes on Big Data Hadoop, Spark to ramp up the teams.
- Tested the end-to-end data flow on TB+ datasets, running & fine-tuning different machine learning algorithms & its optimization.
- Visual representation of Results & summary presentation.
- Defined data landscape, showcased prototypes & implemented predictive Analytics solutions to Biz stakeholders.
- Delivered the biggest Enterprise IT Transformation in Confidential history that put a new data landscape involving SAP suites, Salesforce, Tera data, SAP BW, Micro strategy etc.
- Developed Project Plans using MS Project.
- Led Global teams across broad technical and business disciplines.
System & Business Analyst
- Deployed many large-scale & Innovative Supply Chain solutions with OEM, ODM & Suppliers using Rosetta net/EDI standards using SAP SD, MM, WM, Microsoft BizTalk, TIBCO.
- Delivered a no of technical on-site classes to Confidential worldwide developers on Big Data Technologies, SAP ABAP, DB Performance Tuning, and System Administration for many years.
- Strengthened the internal competencies contributing an annual cost savings of $100K.
- Led the design, development and deployment of enterprise Data solutions involving SAP BW, SAP BO, Tera data.
- Improved the consistency, security, privacy, recoverability and accessibility of data.
- Coded programs in ABAP, ALE, TIBCO & SAP BW & implemented Sales Order, Warehouse Solutions resulting in increased efficiency of the supply chain process, 40% reduction of headcount due to automation.
- Developed ABAP Programs in Sales & Shipping Applications that replaced using PowerBuilder Legacy App saving $1M and improving the productivity and efficiency by 50%+.
- In sourced projects from SIN and HK.