Anu Srivastava

Created an application that allows users to upload and query various document types (PDF, XLSX, DOCX, PPT, JPG, etc.) using advanced natural language processing and document management capabilities.

Implemented a robust system for efficient document retrieval and accurate question-answering, incorporating dynamic embedding and model management for optimized performance and resource utilization.

Indexed documents using Azure Cosmos DB and integrated cloud storage solutions, ensuring efficient retrieval and scalability.

Optimized the system's capabilities to deliver accurate & diverse responses, enabling seamless querying of up to 100 documents with response time upto 20-25 sec.

Achieved a 95% accuracy rate for both fine-grained and holistic view queries using the Retrieval-Augmented Generation (RAG) model

To identify similar products sold by different competitor websites using

title / attribute-based matching and Brand + MPN matching.
Strategize pricing according to the same products sold in competitor’s
website per stocking unit.

Analysing the customers based on their booking information/data and

segmenting to classes: Luxurious, Ravel, Explorer etc.
Assigning rank and group customers based on the recency, frequency and
monetary total of their recent transactions to identify the best customers and
perform targeted marketing campaign

Collaborated with data engineers and operation team to perform data
extraction to fit the analytical requirements.
Work with NLTK library to NLP data processing and finding the patterns.
Perform analysis to assess the quality of the data, determine the meaning of
the data, and provide data facts and insights.
To develop a various machine learning algorithm and statistical modelling for
analysis purpose.
Develop programs to extract the data needed, prepare data for further analysis