ANIL KUMAR LENKA

Sugama Layout, *nd A Cross,

Nyanappanahalli, Bangalore-560068, India

Contact: +91-973*******, E-mail:ad4tmv@r.postjobfree.com

EDUCATIONAL CREDENTIALS

MS (Computer Science & Data Processing-Mathematics) with 8.16/10 CGPA from IIT, Kharagpur, India

(2004 -2006).

MCA(Computer Science) with 72% from Berhampur University, Berhampur, Odisha, India (1999-2002). PROFESSIONAL EXPERIENCE

20+ years of experience on AI, research, design, development, Architecture, consulting, leading & product delivery on AI, ML, DL, LLM, RL, Cognitive Computing, Image Processing, Computer Vision, NLP, Pattern Recognition, OCR, Augmented Reality, Topic Modeling, Segmentation & Recommendation (MAB), RPA, product strategy & engineering.

Expertise in classification, clustering, recommendation, detection, recognition & tracking (Signature, Face, Object), ML & DL Chatbot, Sentiment Analysis, Topic Extraction, Text analytics, Process Automation

Experience in architecting & building the solutions starting with Proof of concept to Pilot, Robotic Process Automation, solution productization, provide guidance, define the strategy & roadmap to the team in the form of reference architectures, guidance principles and reference implementations.

Providing Cognitive solutions to leading enterprise businesses in banking & finance, Insurance, Healthcare, Retail etc.

Strong Experience in building real-world AI/ML systems & Productizing & Scaling them in a large-scale, distributed model & software engineering practices such as version control, system integration, continuous delivery, unit testing, documentation, release management.

Identify the industry leading Cognitive solutions / framework which match with client requirements & Implement, such IBM Watson, TensorFlow, Keras, PyTorch, Scikit-learn, NLTK etc.

Comprehensive experience in Innovation & Research, contributed IP/patent.

Expert in C, C++, Java, Python, OpenCV, OpenNLP, Multithreading, STL & Design Pattern.

Solutioning experience with SQL, NOSQL databases, data streaming & integrating structured & unstructured data.

Experienced in Windows, Linux, UNIX & Android operating systems. Experience in cloud platform (GCP, AWS, Bluemix)

Experience in Agile product development methodologies & following best scrum practices.

Leading, organizing and managing the technical XAI team of data architects, data models, engineers and providing leadership, guidance, and mentoring for analytics \ deep learning frameworks and evangelize the vision to the organization.

Experience in leading & managing teams. Handled multiple roles – Developer, Team lead, Project Lead, and Architect. Ability to work with a multi-technology/cross-functional teams & customer stakeholders to guide/managing a full lifecycle of AI solution.

Worked with different clients across multiple geographies India, USA, Japan, Canada, UK & Germany.

Good communication skills, interpersonal skills, self-motivated, quick learner, team player. TECHNICAL SKILL

Operating Systems MS DOS, Windows, Linux, Unix, Android Programming C, C++, Java, Python, OpenCV, VC++, MFC, OpenCV-android-sdk, OpenNLP, R Frameworks TensorFlow, Keras, PyTorch, Bluemix, Watson (Discovery, Assistant, Knowledge Catalog, Visual Recognition), Docker, Kubernetes, Kubeflow, Kserve, flyte, Kafka, Spark, Scikit- learn, Tesseract, ABBYY, Omni Pages, Datacap, Luminoth, Jenkins, IQBOT, AWS, GCP Design Language OOPS, UML

Database DBT, Trino, MongoDB, MySQL, Oracle

Scripting Java Script, Linux–Shell Scripting, Avenue (ArcView) GIS ArcGIS 9.0, ArcView3.2a, Erdas8.6

Web Technology Html, XSLT, JSON

Tools & Utilities Visual Studio, gdb, SVN, Git, Eclipse, jMonkeyEngine, ImageMagick, Weka, Git, JIRA, Confluence, bitbucket

Domain

knowledge:

AI, Machine Learning, Deep Learning, Image Processing, Computer Vision, NLP, OCR, Banking & Finance, Android Application

CAREER HISTORY

1 Technical Architect (XAI) HCL Software, Bangalore Jun 2021 – Till date 2 Senior Architect (Cognitive) Automation Anywhere, Bangalore Aug, 2019 – Jun, 2021 3 Senior Data Scientist IBM, Bangalore Apr, 2016 – Aug, 2019 4 Senior Consultant Wipro Technology, Bangalore Mar, 2013 – Apr, 2016 5 Senior Technical Lead HCL Technology, Chennai Mar, 2011– Mar, 2013 6 IT Analyst Tata Consultancy Services, Chennai Oct, 2009 – Mar, 2011 7 Member Research Engineer Cranes S.I. Ltd. Bangalore Oct, 2006 – Oct., 2009 8 Junior Project Assistant SRIC, IIT, Kharagpur Mar, 2003 – Feb, 2006 CURRENT ROLES & RESPONSIBILITY

Responsible for understanding of business/technical problems, come up with best-fit architecture, propose techniques, frameworks, algorithms, provide technology consultation, develop the solution & deployment of the solution using the next generation technologies like AI, ML, Deep Learning, NLP, CV, LLM & RPA.

Design, develop & evaluate predictive ML/AI models using metrics that quantify model performance, feature success & customer value. Demonstrate, showcase, and deployed different AI application applying Machine learning, deep learning-based segmentation, classification, recommendation to automatically B2B and B2C application service.

Architect & develop a highly scalable, distributed, multi-tenant set of micro-services backend solution for Commerce, DX, Volta MX, Domino and Unica.

Build solution design & implementation of large-scale futuristic data architecture, real-time data pipelines for data curation, feature engineering and machine learning on enterprise/open-source tools, transitioned data & AI workloads to cloud platforms (AWS, GCP, Azure)

Lead the end-to-end technology architecture & design of complex, enterprise-level Cognitive applications

& systems.

Provide visionary leadership to the XAI data science team, setting the strategic direction and goals.

Stay updated with the latest trends in data science and promote innovation in data analytics and modeling techniques.

PUBLICATION

1. “A new approach for university timetabling problems” International Journal of Mathematics in Operational Research 01/2013 - ISSN:1757-5869. By R. P. Badoni, D.K. Gupta, Anil K. Lenka(2013). 2. “A Backtrack-Free Algorithm for Course Timetabling Problems”, International Journal of Computer Science (IJCS). By Lenka A. K., Gupta D. K. & Sen D. J. (2006). 3. "DRIS: A Decision making tool for planers", GIS Development pvt. Ltd. Noida(UP), India. By Chakrobarty, D., Ghose, M.K., A Jeyaram & Lenka, A.K. (2005). 4. "District Resource Information System", ISRS SYMPOSIUM, ISPRS WG VII/3 WORKSHOP & ISRS, Annual convention 2003, Thiruvananthapuram, India. By Chakrobarty, D. & Lenka, A.K.(2003). PATENT

1. “Methods for Assessing Image Change and Devices Thereof” By Anil Kumar Lenka, Raghavendra Hosabettu, Abhijith Vijaya Kumar Rugminibai. Publication number: US9633050 B2, Link: https://www.google.com/patents/US9633050

2. “Methods & Systems for Determining User Attributes” By Anil Kumar Lenka, Raghavendra Hosabettu, Raja Sekhar Reddy Sudidhala, Kiran Kumar C S. Publication number: US20150206154 A1 Link: https://www.google.com/patents/US20150206154 3. “Systems & Methods for Recognizing Alphanumeric Characters” By Raghavendra Hosabettu, Anil Kumar Lenka. Publication number:US20160086056 A1

Link: https://www.google.com/patents/US20160086056 4. “Method & System for Recognizing Characters” By Raghavendra Hosabettu, Anil Kumar Lenka. Publication number: US9373048 B1, Link: https://www.google.co.in/patents/US9373048 5. “Method & System for Facilitating Operation of an Electronic Device” By Anil Kumar Lenka, Raghavendra Hosabettu. Publication number: 201702, Link: https://www.google.com/patents/US20170286201 6. “System & method for Automobile Oil Life Estimation” By Anil Kumar Lenka, Raghavendra Hosabettu, Publication number: US9373048 B1, Link: http://www.google.com.gi/patents/US9595097 7. “Methods & Systems for Determining an Equipment Operation based on Historical Operation Data” By Raghavendra Hosabettu, Anil Kumar Lenka. Publication number: 201********, Link: https://www.google.com/patents/US20170262297 8. “System & method for automatic detection, extraction & enhancement of handwritten signatures with associated signatory names in scanned documents” by Saigeetha A Jagannathan, Anil K Lenka, Naman Mathur, Yosha Singh Tomar, Ashish A Rao, Prachi Rani, Gaurav S Nandode. Submitted at IBM, 2019.

PROJECT ANNEXURE

Project Name Code generation using generative AI(LLM) Client HCL Domino, HCL Software

Duration Jan 2024 – Till Now

Environment Windows/Linux

Technologies Retrieval Augmented Generation (RAG), LLM, Pinecone, Python, NLP, Docker, BigQuery, GCP, Cloud Run

Domain Machine Learning, NLP, Deep Learning, Generative AI Role Architect, Data Scientist, Designer, Developer & Reviewer. Responsibilities Provide guidance & architecture support to development teams & oversee the development from initial concept to production deployment. Architect & develop a highly scalable, distributed, multi-tenant set of micro-services backend solution. Work closely with the business teams to identifying & co-developing use-cases that can deliver higher business impact with application of AI/ ML/DL.

Summary Code generation using LLMs are the task of generating efficiency and accurate lotus script to volt script code for domain application. The model trained with huge sample code of volt script, to adapt its language understanding capabilities. The fine-tuning process offers considerable advantages, including lowered computation expenses and the ability to leverage cutting-edge models without the necessity of building one from the ground up. Fine-tuning tailors the model to have a better performance for code translate tasks, making it more effective and versatile in real-world applications. The main idea is to leverage the knowledge the model has gained from a large, general dataset and apply it to a more specific or related task.

Project Name Retrieval Augmented Generation for AI Chatbots using LLM Client HCL Domino, HCL Software

Duration Jan 2024 – Till Now

Environment Windows/Linux

Technologies Retrieval Augmented Generation (RAG), LLM, Pinecone, Python, NLP, Docker, BigQuery, GCP, Cloud Run

Domain Machine Learning, NLP, Deep Learning, Generative AI Role Architect, Data Scientist, Designer, Developer & Reviewer. Responsibilities Provide guidance & architecture support to development teams & oversee the development from initial concept to production deployment. Architect & develop a highly scalable, distributed, multi-tenant set of micro-services backend solution. Work closely with the business teams to identifying & co-developing use-cases that can deliver higher business impact with application of AI.

Summary Retrieval Augmented Generation (RAG) is a technique where enrich the LLM prompt with additional context specific to domain real-time data, improving contextualization, and providing up-to-date responses from LLM model. Implemented different module here, load different format training documents and Prepared clean documents to build internal knowledge base and specialize the domain chatbot using Volt MX domain data. Created text embeddings using different embedding model and store the training data in vector store, RAG performs a vector similarity search to add supplemental context in the prompt to a Large Language Model (LLM) query through with retriever interface. Project Name Content based Recommender System (Offer based User Recommendation) Two Tower Model Architecture

Client Unica, HCL Software

Duration Sep 2023 – Jan, 2024

Environment Windows/Linux

Technologies Python, NLP, TensorFlow, Keras, Docker, Kubernetes, BigQuery, GCP, cloud run Domain Machine Learning, NLP, Deep Learning

Role Architect, Data Scientist, Designer, Developer & Reviewer. Responsibilities Design, develop & evaluate predictive ML/AI models using metrics that quantify model performance, feature success & customer value. Provide guidance & architecture support to development teams & oversee the development from initial concept to production deployment. Work closely with the business teams to identifying & co-developing use- cases that can deliver higher business impact with application of AI/ ML/DL. Summary Developed Two Tower Model Recommender delivery of offers to all customers based on offer content, customer activity, and demographic data to generate a ranked list of the best-suited customers for specific offers. Two Tower Model Recommender Algorithm provide Effectively personalized recommendations to customers, Consideration of Multiple Data Types, including customer interactions, offer content, and demographic information, allowing for a comprehensive understanding of user preferences. to optimize marketing expenditure, Optimization conversion rates, and deliver a more personalized experience to customers. The AI model's continuous learning loop, involving the iterative process of sending targeted offers, collecting data, and refining recommendations, is geared towards fine-tuning personalized offer strategy. Project Name Collaborative based Recommender System (Segment based Offer Recommendation) Client Unica, HCL Software

Duration Sep 2023 – Jan, 2024

Environment Windows/Linux

Technologies Python, NLP, TensorFlow, Keras, Docker, Kubernetes, BigQuery, Cloud Run, GCP Domain Machine Learning, NLP, Deep Learning

Role Architect, Data Scientist, Designer, Developer & Reviewer. Responsibilities Provide guidance & architecture support to development teams & oversee the development from initial concept to production deployment. Architect & develop a highly scalable, distributed, multi-tenant set of micro-services backend solution. Work closely with the business teams to identifying & co-developing use-cases that can deliver higher business impact with application of AI/ ML/DL.

Summary Implementing a collaborative filtering model for personalized offer recommendations tailored to specific customer segments, based on historical responses to different event types captured in the dataset. Utilize the historical responses to establish correlations and similarities between customer preferences within the same segment. Generate a ranked list of offers for each segment based on the collaborative filtering model's predictions. Project Name AI Search Optimisation using Did you mean, Automated Synonyms Client Commerce, HCL Software

Duration May 2023 – Sep, 2023

Environment Windows/Linux

Technologies Python, NLP, TensorFlow, Keras, Docker, Kubernetes, BigQuery, GCP, Cloud Run Domain Machine Learning, NLP, Deep Learning

Role Architect, Data Scientist, Designer, Developer & Reviewer. Responsibilities Provide guidance & architecture support to development teams & oversee the development from initial concept to production deployment. Architect & develop a highly scalable, distributed, multi-tenant set of micro-services backend solution. Work closely with the business teams to identifying & co-developing use-cases that can deliver higher business impact with application of AI/ ML/DL.

Summary AI search collects data from various sources, including search queries, browsing behavior, social media interactions, purchase histories and utilize advanced algorithms and Machine Learning (ML) techniques to analyze this data, understanding user intent, context, identifying patterns and generating actionable insights to deliver highly relevant and personalized search results with search result content ranking. Implemented advanced search engine capable of understanding the semantic context of the search queries. By employing Sentence Transformers for contextual embeddings, it is aimed to deliver highly relevant product suggestions that align well with the user's intent. Along with Did You Mean Correction model, which helps users find accurate and relevant search results, even when they make spelling mistakes or enter incorrect queries, It is suggesting corrections considering based on the location of the query coming from, trending interest in a query and past searches, etc. Also applying Automated Synonyms, the use of natural language processing and machine learning techniques to automatically generate alternative words or phrases that have similar meanings to a given query. These synonyms can be generated based on various criteria, such as similarity in meaning, context, frequency, or usage. automated synonym detection system leveraging various tools and models such as KeyBERT, WordNet, FastText, Sentence Transformers, and the FAISS index. Each of these components played a crucial role in enhancing the system's capability to handle text data effectively.

Project Name Product Catalog Optimization using AI Client XAI, HCL Software

Duration Jan 2023 – May, 2023

Environment Windows/Linux

Technologies Python, OpenCV, TensorFlow, Keras, Docker, BigQuery, GCP, Cloud Run Domain Machine Learning, Deep Learning

Role Architect, Data Scientist, Designer, Developer & Reviewer. Responsibilities Design, develop & evaluate predictive ML/AI models using metrics that quantify model performance, feature success & customer value. Provide guidance & architecture support to development teams & oversee the development from initial concept to production deployment. Work closely with the business teams to identifying & co-developing use- cases that can deliver higher business impact with application of AI/ ML/DL. Summary Product Catalog is online or offline marketing information for all the products of an eCommerce industry wants to sell to customers, designed to display relevant product details including product features, descriptions, dimensions, price, weight, availability, color, and more published on various sales channels that help customers make informed purchase decisions. Product catalog optimization system is developed using various methods for automatic product tagging, generating auto product caption or short description and auto identifying product branding, which can help dynamically create or update complete, consistency, accurate product data information, which improve the ecommerce businesses manual error pro system. Implemented 3 deep learning modules having auto training and prediction pipeline.

Project Name XAI Digitization (Image Data Extraction) Client Volt MX, HCL Software

Duration Jul 2022 – Till Now

Environment Windows/Linux

Technologies Python, NLP, OpenCV, tesseract, TensorFlow, Keras, Docker, BigQuery, GCP, Cloud Run Domain Machine Learning, NLP, Deep Learning

Role Architect, Data Scientist, Designer, Developer & Reviewer. Responsibilities Design, develop & evaluate predictive ML/AI models using metrics that quantify model performance, feature success & customer value. Provide guidance & architecture support to development teams & oversee the development from initial concept to production deployment. Work closely with the business teams to identifying & co-developing use- cases that can deliver higher business impact with application of AI/ ML/DL. Summary Digitization is the process of converting image information into a computer-readable format(digital). In order to gain real insights from your data. The objective of this solution is to Extract the text and other components information from any image document and associate the corresponding relation between text data and components. The different information and meta data extraction from documents can be divided into different category:

Detect and extract text extraction using tesseract (OCR Data Retrieve Service)

Detect and recognize different image components (Input box, Button, etc.) using CNN model.

Detect checkbox and radio button (Checkboxes/Radiobuttons Localization and CNN Model (Feature Extractor and Classifier) recognition method).

Mapping between text component with Input box components (Key-Value pair) Project Name Multi-armed bandits for Promotion Recommendation System Client Commerce Signal, HCL Software

Duration Feb 2021 – Jul, 2022

Environment Windows/Linux

Technologies Python, NLP, TensorFlow, Keras, Docker, Kubernetes, BigQuery, GCP, Cloud Run Domain Machine Learning, NLP, Deep Learning

Role Architect, Data Scientist, Designer, Developer & Reviewer. Responsibilities Design, develop & evaluate predictive ML/AI models using metrics that quantify model performance, feature success & customer value. Provide guidance & architecture support to development teams & oversee the development from initial concept to production deployment. Work closely with the business teams to identifying & co-developing use- cases that can deliver higher business impact with application of AI/ ML/DL. Summary Organizations use recommender systems to increase customer engagement and revenue. Collaborative or content-based recommendation system that makes recommendations based on previous historical data of users or product. Most of the existing recommendation system, do not work if there are no such data (cold-start problems), but still, we need to attract the new user to providing the appropriate recommendation without the historical data. Here introduce an efficient Multi-Armed- Bandit-based reinforcement learning method correctly decide when to explore or exploit. Implemented Epsilon-Greedy, Upper Confidence Bound, Thompson Sampling, these algorithms ultimately try & do a trade-off between exploration & exploitation to identify optimal strategy and execute online marketing robust recommender systems. we also experimentally test our approach against popular state-of-the-art product Recommendation and Promotion effectively irrespective of the type of data used. Project Name Dynamic Customer Segmentation

Client Commerce Signal, HCL Software

Duration Jul 2021 – Fab, 2022

Environment Windows/Linux

Technologies Python, NLP, sklearn, TensorFlow, Keras, Docker, Kubernetes, BigQuery, GCP Domain Machine Learning, NLP, Deep Learning, Commerce Role Architect, Data Scientist, Designer, Developer & Reviewer. Responsibilities Provide guidance & architecture support to development teams & oversee the development from initial concept to production deployment. Architect & develop a highly scalable, distributed, multi-tenant set of micro-services backend solution. Work closely with the business teams to identifying & co-developing use-cases that can deliver higher business impact with application of AI/ ML/DL.

Summary Customer segmentation is the process of dividing customers into groups based on common characteristics so companies can market to each group effectively and appropriately. All customers share the common need of your product or service, but beyond that, there are distinct demographic differences (i.e., age, gender, education) and they tend to have additional socio-economic, lifestyle, or other behavioral differences that can be useful to the organization. Here we implemented various algorithms K-Mean, MiniBatchKMeans, DBSCAN, Hierarchical, Affinity, GMM model for Emerald application data. Segmentation as per configured feature list, automatically compute the segment number and do the segmentation, Automated segmentation name and insight report. Automated accuracy computation and accordingly accuracy improvement the model can deploy. Segmentation model develops a better connection between customers, increases values and brand appreciation and relationships. Segmentation helps you conduct target specific which results in gaining more business and profit. Project Name Hybrid IQ BOT Engine

Client Automation Anywhere (RPA)

Duration Jan 2020 – May, 2021

Environment Windows/Linux

Technologies Python, OpenCV, Java, C#, NLP, TensorFlow(Luminoth), PyTorch(Detectron2), Keras, AWS, Tesseract, ABBYY, Docker, Kubernetes, Jenkins

Domain Machine Learning, Image Processing, NLP, Deep Learning, RPA Role Project Architect, Data Scientist, Designer, Developer & Reviewer. Responsibilities Senior architect on ML responsible for solutioning of various cognitive RPA projects. Part of the architecture & delivery team & work on defining the task pipeline, propose new technologies to be include in the road map. Interact with customers to understand business requirements, design, develop & build demos, pocs & povs to showcase cognitive systems salutations & provide consulting advice & deliver. Leading the Hybrid IQBot engine team.

Summary Hybrid IQBot Engine is a RPA tool(Automation Anywhere), It is cognitive bot, automates business processes that rely on semi-structured or unstructured data hidden in electronic documents, images, emails & more using the latest AI technologies like Computer Vision, Natural Language Processing (NLP), machine learning (ML) & deep learning without the help of data scientists or highly trained experts & learns by observing people at work increasing your digital footprint. IQ Bot leverages multiple AI techniques to intelligently digitize & extract data to make RPA and/or OCR technology even more effective. IQ Bot keeps learning from corrections made by users getting smarter & more accurate over time. Hybrid IQ Bot Engine purpose-built cognitive automation that integrates with other AI solutions.

Project Name Smart Digitization (IQBOT)

Client Automation Anywhere (RPA)

Duration Aug 2019 – Mar, 2020

Environment Windows/Linux

Technologies Python, OpenCV, Tesseract, ABBYY, NLP, TensorFlow(Luminoth), Docker Domain Machine Learning, Image Processing, NLP, Deep Learning Role Project Architect, Data Scientist, Designer, Developer & Reviewer. Responsibilities Senior architect on ML responsible for solutioning of various cognitive RPA projects. Part of the architecture & delivery team & work on defining the task pipeline, propose new technologies to be include in the road map. Interact with customers to understand business requirements, design, develop & build demos, pocs & povs to showcase cognitive systems salutations & provide consulting advice & deliver. Leading the digitization team, Designed & implemented end-to-end Automation systems for Digitization Information extraction.

Summary This application transforms or convert manual paper-based document to digital computer readable form as per business requirement. It extract information such as Key, Value extraction, table detection, row, column extraction, checkbox/radiobutton detection & recognition, detect signatures & associate the corresponding signatory name, signature verification, Face detection, matching & recognition, Logo, stamp, barcode & other image detection & recognition, Bar Code Detection & recognition, in any type of documents & associate the corresponding OCR result with Metadata. Project Name Cognitive Signature Detection & Verification Client JPMorgan Chase

Duration Feb 2019 – Aug 2019

Environment Windows/Linux

Technologies Python, OpenCV, Tesseract, Datacap, Docker, Nodejs, Imagemagick, NLP, Luminoth. Domain Machine Learning, Image Processing, NLP, Deep Learning Role Project Lead, Data Scientist, Designer, Developer & Reviewer. Responsibilities Interact with customers to understand business requirements. Technology & project roadmap preparation. Developing & deploying classification, segmentation of the image signature & mapping the signature with name using NLP. Designed & implemented end- to-end Automation systems for Digitization & signature detection & verification. Leading the digitization team.

Summary This solution is to detect signatures in any type of scanned image documents & associate the corresponding signatory name. In addition to name, it also maps the signatures to category/class, designation or invoice number depending on the type of document. It can detect any type of signature which can be at any location on the document. The signature may have different orientations & can be overlapped with printed text/images etc. The extracted signature is verified & mapped with its master signature. The metadata including total number of extracted signatures; sign extraction, name & class mapping & signature verification confidence scores is exported into an output json file. The Metadata to be extracted & mapped depends on the type of documents Project Name ORIFLAME – Counter Fraud Solution

Client Oriflame, India

Duration Jan 2019 – Feb 2019

Environment Windows/Linux

Technologies Python, OpenCV, Tesseract, Docker, MongoDB, WDS Domain Image Processing, Machine Learning, NLP, Cognitive Computing & Watson Role Project Lead, Data Scientist, Designer, Developer & Reviewer. Responsibilities Interact with customers to understand business requirements. Technology & project roadmap preparation. Developing & deploying OCR extraction from image & implementing NLP document similarity check for fraudulent detection using NLP & Signature. Designed & implemented end-to-end Automation systems for Digitization & fraudulent analytics. Leading the digitization team. Summary It deals with Automation in Consultant Registration instance in Oriflame & fraudulent detection using Cognitive Digitization Studio. The integrated Cognitive solution investigates multiple facets of a Consultant or Product or Markets. The information extracting from the submitted documents & auto fill the application form, establish Consultant using ID document along with other information, such as face, signature, name, address, gender, age, etc. Finding relationships between registered consultants. Detecting multiple registrations of a consultant. checking personality insights of consultants with Social web. Curated price data & dealer info collection from websites like Amazon & Flipkart for specific cities. A list of all dealers selling Oriflame products from specific cities with a temporal timeline that includes details. The information is collected from a range of structured & un-structured sources, & applied Watson advanced Content Analytics to categorize the information into different facets & fraudulent detection. Project Name Cognitive Digitization Studio

Client IBM, India

Duration Jan 2018 – Jan 2019

Environment Windows/Linux

Technologies Python,

Contact this candidate