Ankur Trivedi, Developer in Gurugram, India
Ankur is available for hire
Hire Ankur

Ankur Trivedi

Verified Expert  in Engineering

Bio

Ankur is a senior data scientist with eight years of experience working with multiple clients ranging from banking, aviation, healthcare, retail, pharma to manufacturing companies with varied data science problem statements. He has helped clients with requirements related to customer churn, acquisition, net promoter score, constrained cost optimization, and video processing for queue wait times estimation. Ankur has hands-on experience with Python, scikit-learn, NumPy, Pandas, and TensorFlow.

Portfolio

Deloitte Consulting
Machine Learning, Modeling, Analytics, SAS, Data Science, Python, Data Analysis...
Deloitte Consulting
Python, Machine Learning, Modeling, Classification, OpenCV, AWS Lambda...
Deloitte Consulting
Python, SAS, JSON, Statistics, Statistical Data Analysis, R...

Experience

  • Python - 10 years
  • Data Science - 5 years
  • Model Development - 5 years
  • Machine Learning - 5 years
  • Analytics - 5 years
  • SAS 9.3 - 4 years
  • OpenCV - 3 years
  • Amazon SageMaker - 2 years

Availability

Full-time

Preferred Environment

Amazon Web Services (AWS), SAS, Python 3

The most amazing...

...project I've created was a production-ready end-to-end framework utilizing camera feeds from an amusement park to estimate queue wait times—built on AWS Cloud.

Work Experience

Senior Consultant

2019 - PRESENT
Deloitte Consulting
  • Developed an end-to-end framework on AWS cloud feeding in various camera feeds to estimate queue wait times for an amusement park utilizing SQS, SNS, AWS Lambda functions, and OpenCV.
  • Simulated internet demand for a SATCOM client at a spatiotemporal level to prioritize upcoming deals and identify the potential congestion matrix in advance.
  • Strategized the expense plan for one of the major healthcare providers to maximize their KPIs while optimizing the spending for enhanced market ratings.
Technologies: Machine Learning, Modeling, Analytics, SAS, Data Science, Python, Data Analysis, Pandas, TensorFlow, Artificial Intelligence (AI), Data Visualization, Apache Spark, Data Engineering, Amazon SageMaker, AWS Lambda, Kubernetes, Amazon EC2, ChatGPT, Amazon S3 (AWS S3), Generative Artificial Intelligence (GenAI), Large Language Models (LLMs), OpenAI, Leadership, LangChain, Minimum Viable Product (MVP), JSON, Statistics, Statistical Analysis, Statistical Data Analysis, Tableau, Mathematical Statistics, FastAPI, APIs, Azure, Google Cloud Platform (GCP), Large Language Model Operations (LLMOps), Retrieval-augmented Generation (RAG), Vector Databases, Pinecone, Applied Statistics, Forecasting, Statistical Methods, Machine Learning Operations (MLOps)

Consultant

2017 - 2019
Deloitte Consulting
  • Performed unsupervised modeling for a major consumer products manufacturing client to identify downtime and increase the production yield as part of building a data-driven smart factory.
  • Developed and implemented a pipeline for feature extraction from customer communication data using latent Dirichlet allocation and sentiment analysis to enhance the performance of the customer churn model utilizing natural language processing (NLP).
  • Created a framework for identifying the potential opportunities for each of the stores for sales representatives of an FMCG company and natural language generation methodology to create effective sales scripts in an automated fashion.
Technologies: Python, Machine Learning, Modeling, Classification, OpenCV, AWS Lambda, Amazon EC2, Amazon S3 (AWS S3), Minimum Viable Product (MVP), JSON, Statistics, Statistical Analysis, Statistical Data Analysis, Tableau, Mathematical Statistics, Azure, Applied Statistics, Forecasting, Statistical Methods, Machine Learning Operations (MLOps)

Business Analyst

2015 - 2017
Deloitte Consulting
  • Created the customer acquisition propensity model for one of the leading US airlines for evaluating the propensity scores using an elaborate dataset of customer’s past historical transactional history, reducing the acquisition cost by 60%.
  • Worked with survey data on airport lounges to identify the pain points, changing trends, and customer satisfaction scores creation along with developing a Tableau dashboard for its consumption by business stakeholders.
  • Forecasted the demand at the stock keeping unit (SKU) level for one of the largest fast-food chains based on their past trends, seasonality, price, along with the temperature and humidity variation happening across different geographies.
Technologies: Python, SAS, JSON, Statistics, Statistical Data Analysis, R, Mathematical Statistics, Applied Statistics, Forecasting

Experience

Customer Churn Prediction Using NLP

Developed and implemented a pipeline for feature extraction from customer communication data using latent Dirichlet allocation, sentiment analysis, and tf-idf methodology to improve the performance of the customer churn model.

I worked on creating features from communication log data, perform topic-modeling to identify broad topics of discussion along with identifying the text sentiment to proactively identify customers at risk of churn.

Education

2010 - 2015

Master of Science Degree in Economics

Indian Institute of Technology, Kanpur - Kanpur, India

Skills

Libraries/APIs

Pandas, NumPy, Scikit-learn, REST APIs, OpenCV, TensorFlow, PySpark

Tools

SAS 9.3, Amazon SageMaker, Plotly, Tableau, ChatGPT, sparklyr, Amazon QuickSight

Languages

SAS, Python, SQL, R

Frameworks

Apache Spark

Platforms

Amazon Web Services (AWS), Databricks, AWS Lambda, Docker, Kubernetes, Amazon EC2, Azure, Google Cloud Platform (GCP)

Storage

Amazon S3 (AWS S3), JSON, PostgreSQL, Neo4j

Industry Expertise

Applied Statistics

Other

Machine Learning, Data Science, Analytics, Modeling, Model Development, Data Analytics, Data Analysis, Big Data, Statistics, Artificial Intelligence (AI), Predictive Analytics, Database Analytics, Mathematics, Consulting, Data Engineering, Lambda Functions, Mathematical Statistics, FastAPI, Natural Language Processing (NLP), Amazon Timestream, Cloud Computing, Complex Data Analysis, Deep Learning, Neural Networks, Deep Neural Networks (DNNs), GloVe, Word2Vec, Forecasting, APIs, Computer Vision, Generative Pre-trained Transformers (GPT), Data Visualization, Generative Artificial Intelligence (GenAI), Large Language Models (LLMs), LangChain, Retrieval-augmented Generation (RAG), Leadership, Minimum Viable Product (MVP), Statistical Analysis, Statistical Data Analysis, Large Language Model Operations (LLMOps), Vector Databases, Statistical Methods, Machine Learning Operations (MLOps), Economics, Econometrics, Topic Modeling, Classification, Data Modeling, GraphDB, Scalable Vector Databases, Amazon Bedrock, OpenAI, Pinecone

Collaboration That Works

How to Work with Toptal

Toptal matches you directly with global industry experts from our network in hours—not weeks or months.

1

Share your needs

Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring