Predicting the Future
by Implementing it.


Senior Consultant

I studied Computer Science from BITS Pilani (Bachelor's degree) and Leibniz Universität Hannover (Master's degree).

Currently, I am working as a Senior Consultant in the DAICA (Digital, AI Controls and Algorithms) team in the Risk Advisory division at Deloitte.

I was born and raised in New Delhi. At present, I live in Düsseldorf.

Technical ExpertiseInformation Retrieval | Natural Language Processing | Machine Learning | Semantic Web | Object Oriented Programming


Leibniz logo

Leibniz Universität Hannover

Hannover, Germany   |   2015 - 2018

  • M.Sc. in Computer Science, with an emphasis on Internet Technologies and Information Systems (ITIS)
  • GPA: 1.1/5 (1.0 best out of 5)
  • Relevant Courses:
    • Simulation Engineering
    • Efficient Algorithms
    • Data Mining
    • Web Science
    • Knowledge Engineering and Semantic Web
    • Algorithms for Internet Applications
    • Foundations of Information Retrieval
    • Stream Data Mining
    • Seminar on Internet Technologies
    • Seminar: Security of Self-organizing Networks
    • Geo-Information Systems
    • Research Project: Building and Querying Semantic Layers for Web Archives
    • Master Thesis: Ranking Archived Documents for Structured Queries on Semantic Layers
BITS logo

BITS Pilani

Dubai, UAE   |   2011 - 2015

  • B.E. (Hons.) in Computer Science
  • GPA: 9.77/10 (10 best out of 10)
Amity logo

Amity International School, Mayur Vihar

Delhi, India   |   2009 - 2011

  • Class XII (CBSE), Science


Research Paper Acceptance at WSDM 2022

University of Halle-Wittenberg | Oct 2021

  • Research Paper on "Query Interpretations from Entity-Linked Segmentations" was accepted at the WSDM 2022 Conference (ranked A*, a top conference for Data Mining and Analysis).

Best Master's Degree award

Leibniz University Hannover | Dec 2018

  • Received certificate for Best Master’s degree for the course M.Sc. Computer Science (ITIS) in the academic year 2017/18 by the Faculty of Electrical Engineering and Computer Science at the Leibniz University Hannover.

Best Paper Award Nomination

JCDL 2017 | June 2017

  • Research Paper on “Building and Querying Semantic Layers for Web Archives” got nominated for “Vannevar Bush Best Paper Award” at the 2017 ACM/IEEE-CS Joint Conference on Digital Libraries (JCDL).

BITS Scholarship for Academic Excellence

BITS Pilani, Dubai Campus | 2011 - 2015

  • Recipient of the scholarship for the entire duration of Bachelor’s Degree. This scholarship is awarded to students maintaining a CGPA greater than 9.0 throughout semesters.


Senior Consultant

Digital / AI Controls / Algorithms, Risk Advisory

Project Experience
  • Banking
    • Cloud-based Processing of Banking Documents: Creation of a document pipeline for processing banking documents using Google DocumentAI Platform.
  • Life Sciences
    • Digitalization of Quality Management: Transform Production and Quality Management systems from heavily documentation based, functionally segregated systems towards an intelligent and data-driven end-to-end solution.
  • Asset Management
    • ML Text Extraction of Securities Prospectuses: Built a prototype that uses AI and rule-based solutions to recognize, extract, and display relevant data from the documents.
    • Explainable AI: Developed a tool which uses Shapley values to explain the decision-making process of Deep Learning models like BERT, RoBERTa and DistilBERT.
  • Certifications
    • Aug 2021: AWS Cloud Certified Practitioner (Amazon Web Services)
    • Jun 2021: BSI IT-Grundschutz-Praktiker (Bitkom Akademie)
  • Miscellaneous
    • Drafting offers and workshop slides for client projects.
    • Preparation of sales presentations for Asset Management firms in the DACH region.
May 2021 - Present | Düsseldorf, Germany
Research Associate

Research Group: Big Data Analytics, Webis Group

Project Experience
  • Query Interpretations from Entity-Linked Segmentations
    • Goal: Interpret ambiguous search engine queries to show more relevant results to the user, answer the query or help fill search engine’s knowledge boxes.
    • Designed and developed an automatic approach that uses query segmentation and entity linking to identify the most reasonable interpretations of a query based on the contained entities.
    • Conducted an experimental comparison on a new corpus of 2,800 queries. It proves that my approach has better interpretation accuracy at a better run time than the previously best methods.
  • Total Recall in Systematic Reviews
    • Goal: Find all relevant documents (“total recall”) given a collection of potentially several thousands of documents somewhat related to a user-specified topic. A single systematic review may take up to 2 years without any machine-assistance.
    • Built a system that reduces the review period by ordering these documents in descending relevance.
    • Implemented several machine learning methods from an existing total recall approach (HiCAL) and tested these on botanical research datasets. The results show that machine learning reduces the human effort by almost 80 percent.
    • Development of a new algorithm that continuously adapts the feature set to the growing user feedback, and combines the current feature set with machine learning (learning-to-rank) to a ranking score.
  • Argumentative Axiomatic Re-Ranking for Medical Search Queries
    • People use search engines to seek health advice online.
    • Using search engines to complete such decision making tasks, users are not able to discern authoritative from unreliable information.
    • As part of a team, we developed an axiomatic approach to re-rank search results obtained by traditional search models, in order to promote more argumentative results for medical queries.
  • Teaching Experience
    • Foundations of Computer Science and Concepts of Modeling
    • Search Algorithms
    • C Programming
    • Software Project Internship (Supervision)
    • Object Oriented Programming
  • Courses Attended
    • SS 2019: Natural Language Processing
  • Reviewing Experience
    • Sub-Reviewer: ECIR 2020 Conference, Lisbon
    • Sub-Reviewer: CHIIR 2020 Conference, Vancouver
  • Online Certifications
    • Dec 2020: Machine Learning, Stanford University (Coursera)
    • Mar 2020: Introduction to the Bash Shell on Mac OS and Linux (Pluralsight)
    • Mar 2020: Competitive Programming (Coding Ninjas India)
    • Oct 2019: Master Object Oriented Design in Java (Udemy)
    • Sep 2019: Complete Python Bootcamp (Udemy)
    • May 2019: Structuring Machine Learning Projects (Coursera)
    • May 2019: Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization (Coursera)
    • May 2019: Neural Networks and Deep Learning (Coursera)
  • Website Maintenance
Aug 2018 - Oct 2020 | Halle (Saale), Germany
Research Associate


Project Experience
  • Prototyped a Question Answering system for an accounting firm.
  • As part of the team, contributed to the development of algorithms in the area of Deep Learning as well as Speech Processing for intelligent smart car systems.
  • Small contributions to the project GEISER which dealt with the analysis of spatial data.
Apr 2018 - Jun 2018 | Bonn, Germany
Student Research Assistant


Alexandria Project (ERC Advanced Grant Project)
  • Research on methods for the semantic and entity-based exploration of Web Archives.
  • Aim of the project was to significantly advance semantic and time-based indexing for Web Archives, to efficiently index, retrieve and explore information about entities and events from the past.
  • Built semantic profiles (“layers”) that describe semantic information about the contents of Web Archives using Entity Linking Tools.
  • Evaluated the semantic layers for complex information needs against keyword-based search systems like Google, Bing and HistDiv.
  • Designed and evaluated statistical and advanced models (PageRank-like) to rank results returned by running queries on these layers.
Volunteer Experience
  • Sep 2016: Member of the Organizing Committee for TPDL 2016 Conference, Hannover
  • May 2016: Member of the Organizing Committee for ACM WebSci’16 Conference, Hannover
Oct 2016 - Jan 2018 | Hannover, Germany
Software Developer (Intern)


Raster Development
  • Handled Multidimensional Geo-data (GRIB, NetCDF, HDF, etc.)
  • Analyzed Raster, Mosaic and Image Service Data Layers.
  • Fixed bugs and changes requested for ArcGIS 10.
  • Validated UI functioning of Raster and Geo-Processing Tools of ArcGIS Pro.
  • Removed potential defects (by Coverity Analysis) in Raster Solutions of ArcGIS 10.
Aug 2014 - Jan 2015 | Sharjah, UAE

Projects (Open-Source)

Screen shot Query Understanding
Query Understanding

Query Interpretations from Entity-Linked Segmentations

Screenshot of Semantic Layers
Semantic Layers

Research Project and Master Thesis on Semantic Layers

  • Code, papers, datasets and other resources for:
    • Building and Querying Semantic Layers for Web Archives JCDL paper and IJDL journal
    • Ranking Archived Documents for Structured Queries on Semantic Layers JCDL paper and poster
  • Link to Repository


Programming Languages


Data Science / Machine Learning

Hugging Face

Semantic Web Technologies

Apache Jena

Integrated Development Environments

IntelliJ IDEA
Jupyter Notebook
Visual Studio

Entity-Oriented Search

Entity Linking
Entity Disambiguation
Word-Entity Embeddings
Query Segmentation

Version-Control Software


Database Management

Openlink Virtuoso (Graph Database)
PostgreSQL (SQL Database)
MySQL (SQL Database)
RocksDB (NoSQL Database)

Web Development



Apache Lucene
Apache Maven
Multithreaded Programming