Aarushi Kapoor

Data Scientist

London, England, United Kingdom5 yrs 3 mos experience

Most Likely To SwitchAI Enabled

Key Highlights

Architected a data platform reducing processing time significantly.
Developed NLP solutions for legal document analysis.
Achieved top 31% rank in Kaggle forecasting competition.

Stackforce AI infers this person is a Data Scientist with expertise in NLP and data intelligence in consulting.

Contact

Skills

Core Skills

Data IntelligencePython (programming Language)Machine LearningMicrosoft Power BiAws

Other Skills

Amazon Web Services (AWS)Analytical SkillsAnalyticsBloggingBusiness DevelopmentC++ClientCommunicationData AnalysisData VisualizationDecision SciencesExploratory Data AnalysisFinanceGenAILarge Language Models (LLM)

About

Achiever | Deliberative | Learner | Relator | Analytical Budding Data Scientist. A self-driven and responsible individual. A quick learner, I love taking challenges and excel in results. Good interpersonal skills, a hard working nature and an easily adaptive aptitude. I believe that self-discipline is a must for being successful in the long run.

Experience

Oxera consulting llp

Data Scientist

May 2024 – Present · 1 yr 10 mos · London Area, United Kingdom · On-site

Architected and implemented query-based data platform for document disclosure from 12-hour to 2-hour processing, accelerating access to case-relevant structured data across 8 million records
Built NLP-powered semantic search pipeline for competition and antitrust litigation, identifying hundreds of relevant claimant documents within hours hours
Developed transformer-based AI comment assistant for expert economic reports achieving 70%+ similarity to regulatory review standards, significantly reducing turnaround time in legal cycles
Implemented automated metadata extraction system for RFI response preparation, processing 6,000+ financial documents with advanced NLP for litigation support
Built multi-language document translation pipeline for merger cases, processing 800+ documents while maintaining legal formatting integrity

Decision SciencesData IntelligencePython (Programming Language)Exploratory Data Analysis

Accenture

2 roles

Data Science Innovation Senior Analyst

Aug 2023 – May 2024 · 9 mos

Independently designed and productionized QA/QMS data pipelines
Designed, built and managed dashboards for reporting QA/QMS data
Provided tech support for QA/QMS teams

Data Scientist Analyst

Feb 2022 – Jul 2023 · 1 yr 5 mos

Independently established end-to-end automated refresh pipeline for 68% faster daily refresh
Built and maintained supply chain dashboards to improve global stock management by 3%
Lead in-dept data analyses for discovery and dashboard debugging

Microsoft Power BIAmazon Web Services (AWS)Microsoft Power AutomateSQL Server Management StudioAWS

Wolf & badger

Data Analyst

Aug 2021 – Jan 2022 · 5 mos · Greater London, England, United Kingdom

Integrated Big Data Analytics software on Google cloud (Looker) with customer service platform (Hubspot) to facilitate easy communication with brand partners.
Developed and maintained multiple dashboards catering to brand partners and customers which helped with business decisions on Looker.
Modelled data in Data Build Tool (DBT) to enable analysis and improvement of brand onboarding.

Bluepi consulting pvt. ltd.

Data Science Intern

Oct 2019 – Aug 2020 · 10 mos · India

Worked with the Data Science team for forecasting sales in retail. My projects encompassed research based new approaches to improve results, which would not only be statistically correct but also bring value to the partner company - asking simple but important questions like should the forecasted numbers be rounded up or down.
I also worked on probabilistic forecasting models using NGBoost which had just been released at that time. I could comfortably customise it to my needs even after being new with python programming.
Finally, the team and I completed in the M5 Forecasting Accuracy challenge on Kaggle. This involved forecasting sales for Walmart 28 days in advance over 3 states for 3 months. We achieved the top 31% rank on our first competition. I learnt a good deal of feature engineering for time series modeling and gained more knowledge on LSTMs and LightGBM models.
I also wrote statistical blogs for the company which can be found at - https://www.bluepiit.com/blog

Kirori mal college, university of delhi

Research Intern

Jan 2019 – Mar 2019 · 2 mos

Data Analyst under Dr. Benu Gupta, for a research project funded by the Ministry of Youth Affairs and Sports. Studied the Big Five Personality traits (Five Factor Model) and the Group Cohesion using the GEQ to give an analysis of players of different types of sports and gender for performance improvement. Also created intuitive visualisations for the findings using R programming.

Fabindia overseas pvt ltd

Digital Marketing Intern

Jun 2018 – Jul 2018 · 1 mo · New Delhi Area, India

Worked on Google Adwords and Google Business. Used R programming to successfully optimise Keyword Search methods and reduce time and effort taken by 60%-90%. Created Digital Ads. Performed new website testing.