[reverse chronological order]
“By 2050, the world will need to feed two billion more people without an increase of arable land. IBM is combining power weather data – including historical, current and forecast data and weather prediction models from The Weather Company – with crop models to help improve yield forecast accuracy, generate value, and increase both farm production and profitability.
Using a suite of customized low-cost solutions that help key stakeholders make faster, more informed agricultural decisions, IBM Watson Decision Platform for Agriculture delivers AI-driven insights for the agriculture ecosystem.”
In this role, I was responsible for technical product management, platform architecture and engineering effort for Watson Decision Platform focusing on use cases in Agriculture.
“The Weather Company provides the world’s leading technology platforms and services leveraging weather and related data. Our organization delivers billions of forecasts a day around the world via seamless cross-platform technology. We connect newscasters, airline pilots, energy traders, insurance executives, state agency employees, retail management and more to the weather intel they need, on any device. We aggregate the deepest, richest data sets — both business and consumer — to deliver personal, reliable and actionable weather information, analytics and insight.“
In this role, I was responsible for architecture and engineering team for building solutions to support several data and analytics use-cases, data governance, data-science based insights, curated data lakes, geo-spatial/location data processing, etc.
“IBM Insight Cloud Services deliver data and data-science based insights by combining internal data with external data about people, events, geo-spatial factors, and businesses from sources such as Twitter and The Weather Company. These external datasets have been enriched, refined and statistically validated by IBM data scientists. Insight Cloud Services takes the complexity of analyzing multiple sources of data out of the equation using specialized analytic models developed by IBM for businesses to find more and more relevant signals in the data.“
Learn more here – Information and Insight as a Service
In this role, I led a team responsible for development of an automated data ingestion framework to support governance and on-boarding of open and proprietary data sets, ensuring proper cataloging, profiling and data quality for self-service and client specific data science work. Supported delivery of data science based insights for several customers across retail, apparel and energy verticals.
“Fraud and financial crimes trigger financial losses, cause significant operational costs, erode consumer confidence, destroy brand image and drains the potential for core business innovation. A new, holistic approach is needed to not only handle, but proactively anticipate and respond to threats. IBM Counter Fraud Management is a new, next generation offering, delivered as a single, integrated solution, that addresses all phases of enterprise counter fraud measures.”
Read more here – CFM AML Compliance Use-case
I led the design and development of several strategic features for the solution, like a comprehensive stewardship console for end-to-end management of analytics, a rule-based framework for triggering actions based on scoring thresholds, suspicious activity reporting (SAR) workflow, alert management functionality, device fingerprinting, multi-language support, etc to help grow revenue to over $10M spanning large enterprise customers.
“Semantixs is a system for ontology-guided extraction and semantic representation of structured information from unstructured text, implemented as a web application, that can extract, represent and visualize domain-specific information from free-text in the form of complex (and simple) relationships. It especially enables extraction of a subset of nested complex relationships, where the main subject refers to an internal clause through a verb. (e.g., Joe reports that Jim is a reliable employee).”
Read more here – ICTAI Conference Paper.
As the lead researcher on the project, I devised the algorithm, ran a series of experiments to validate underlying thesis and and published the results in the International Conference on Tools with Artificial Intelligence. I also laid down the system architecture, design and interaction across several components (Stanford Parser, Jena, Google Web Toolkit and core algorithm modules), and wrote the entire code for a system that was open sourced and downloaded across 56 countries.
“Reference Data Management (RDM) is an offspring of Master Data Management (MDM) functionality to provide the processes and technologies for recognizing, harmonizing and sharing coded, relatively static data sets for “reference” by multiple constituencies (people, systems, and other data).”Read more here – RDM Field Report by the MDM Institute& here – IBM Redbooks Publication
As a technical lead, I contributed to every aspect of product development from analyzing requirements, breaking down technical specs, developing functional design and making regular code contributions across the entire stack, evolving build infrastructure, hardening, security and performance improvements. Later, I transitioned into a customer advocate role, providing technical guidance to several large customers on their RDM implementations resulting in revenue growth to over $5M.
“IBM® InfoSphere® Blueprint Director is designed to help IT departments define and manage their information projects, from initial sketches through final delivery. Creating a well-documented, end-to-end blueprint of both the business and technical vision for an information project can help IT departments align business requirements with enterprise and reference architecture and encourages a standardized approach that minimizes rework. By representing the project vision across all domains (e.g. data integration, data archiving, test data management, application retirement, data warehousing, and business intelligence), blueprints can help data architects avoid siloed thinking and misalignment with business priorities.“
Read more here – Best practices for IBM InfoSphere Blueprint Director
As a software engineer, contributed towards the first release of blueprint director to take it from an advanced technology concept to a shipped product.
“Master data management (MDM) provides a trusted view of critical entities typically stored and potentially duplicated in siloed applications – customers, suppliers, partners, products, materials, accounts, etc. IBM’s Master Data Management (MDM) solutions provide a trusted, 360 degree view of your data. This helps achieve customer centric objectives and business results. “
Read more here – MDM whitepapers
As an engineer and researcher, developed several product features and domain extensions helping grow the business in new industry verticals, led several forward-thinking initiatives in and around w3, data mashups, integration patterns, linked data, etc.