Summary
Overview
Work History
Education
Skills
Certification
Projects
Accomplishments
Websites
Skills Utilized:
STRENGTHS
Awards
Publications
Timeline
Generic
Dr. MANASA NOOLU PhD

Dr. MANASA NOOLU PhD

Brussels

Summary

Self-motivated Data Scientist offering several years of leadership experience across various industries. Methodical with significant experience in data mining and statistical analysis. Excellent problem-solver with history automating processes and driving operational enhancements.

Overview

16
16
years of professional experience
1
1
Certification

Work History

Data Scientist

Ascent Fund Services
11.2021 - 08.2024
  • Leading Big Data and Data Science efforts using machine learning techniques for crypto analysis, predicting the optimal trading points for platforms such as HUOBI, CRYPTOCOM, DERIBIT, OSL, KRAKEN, BITFINEX, and BITGET, leveraging Docker for model deployment and scalability
  • Analyzed transaction data to identify price fluctuations using machine learning models, improving investor retention strategies and ensuring timely responses to market trends
  • Leveraged cutting-edge NLP techniques to extract insights from transactional data, enabling proactive identification of price fluctuations, and empowering investor retention strategies through personalized recommendations using LangChain
  • Championed the development of AI-powered models with diverse applications in business analysis, ensuring adaptability to dynamic market conditions by integrating Docker and machine learning workflows for efficient model management
  • Orchestrated the automation of data retrieval processes using Al-driven solutions, streamlining the acquisition and dissemination of Portal Data for Ascent CSMs, with containerized solutions via Docker for efficient deployment
  • Employed AI algorithms to manage Coin Markets Rates for FX Loaders, optimizing data integration and analysis for informed decision-making, and using machine learning techniques such as linear regression and random forest regression to enhance predictive accuracy
  • Guided the team on utilizing machine learning methods to improve task efficiency, employing Docker for seamless deployment and handling client requests to address and resolve data-related issues efficiently

Data Scientist

KBC Bank en Verzekeringen
03.2021 - 08.2021
  • Optimized machine learning models within the model factory to build customer journeys, improving predictive accuracy (ROC curve) and personalization using MLOps pipelines for continuous integration and deployment
  • Led feature engineering and machine learning modeling for detecting interconnectedness of companies in a community through graph network analysis, leveraging Spark for distributed data processing to handle large- scale datasets
  • Developed a generic machine learning framework for the team to leverage across varied projects, utilizing MLOps practices to ensure efficient and scalable deployment of models, enabling faster business analysis and decision-making
  • Conducted in-depth machine learning-driven analysis and proposed data-driven solutions to address complex business needs, incorporating Spark for efficient processing of large datasets in real-time analysis

Junior Data Scientist

BeCode.org
10.2019 - 03.2021
  • Employed sophisticated analysis systems to extract information from large- scale data using data science skills, including machine learning techniques
  • Utilized deep learning models to provide insights and proposals supporting business improvements
  • Conducted business analysis to understand business needs and translate them into conceptual designs
  • Leveraged Docker for containerizing machine learning applications, ensuring scalability and seamless deployment across environments

Assistant Professor

VNR VJIET
10.2008 - 07.2019
  • Designed and coordinated hands-on activities to enhance student's interactions and critical thinking skills
  • Served on various committees concerned with academic planning, cultural program organizing, administrative-initiated projects
  • Fostered a dynamic learning environment by encouraging active participation, facilitating discussions, and providing constructive feedback to promote student growth and development

Education

Doctor of Philosophy (PhD) - Computer Vision and AI

Jawaharlal Nehru Technological University
Hyderabad, India
01.2024

Master of Technology - SE

Jawaharlal Nehru Technological University
Hyderabad, India
09.2011

Bachelor of Technology - CSE

Jawaharlal Nehru Technological University
Hyderabad, India
05.2007

Skills

  • Data Science
  • Machine Learning/ Deep Learning/NLP
  • Python, PySpark, Hive, H2O
  • Tensorflow & Keras
  • Flask API, Docker, Heroku
  • Generative AI
  • Computer Vision

Certification

  • Neural Networks and Deep Learning Coursera Certificate ID: USG68365QG7K
  • Build Basic Generative Adversarial Network (GANS) Coursera certificate ID: LSLGRAWLLDXH
  • Natural Language Processing with Classification and Vector Spaces Coursera

Projects

DETECTION OF TEXT IN VIDEO USING DYNAMIC BOUNDING BOX GENERATION WITH FASTER ADAPTIVE REGIONAL PROPOSAL NETWORKS, Researcher Sep 2016 - Jan 2024 Developed an innovative approach for text detection in videos, a critical step in Optical Character Recognition (OCR) systems, with applications in FASTag, document analysis, and smart vehicle navigation. Addressed challenges such as complex backgrounds, poor illumination, and text distortion through hybrid preprocessing techniques. Introduced enhanced text filling, angular rotational gradient, and enhanced Gaussian function to improve edge information and visibility of text data. Implemented a novel feature extraction method using enhanced thinning to extract characters and regions, enabling dynamic bounding box ratio computation. Designed a hybrid architecture incorporating Faster Adaptive Regional Proposal Networks (FARPN) for end-to-end trainable text identification, surpassing traditional methods. Conducted comparative analysis with Faster Region Convolutional Neural Network with a Regional Proposal Network (FRCNN-RPN), demonstrating the superiority of the proposed approach in terms of accuracy and speed. Developed an interface for visualizing detected text in videos. Achieved 91.2% accuracy on the ICDAR 2013-15 "text in video" dataset, showcasing the effectiveness of the FARPN methodology.

Accomplishments

  • Innovated hybrid preprocessing techniques for improved text detection in videos.
  • Introduced dynamic bounding box ratios and FARPN architecture for enhanced accuracy and speed.
  • Demonstrated superior performance compared to existing methods through extensive experimentation and evaluation.

Skills Utilized:

  • Computer Vision
  • Deep Learning
  • Image Processing
  • Python Programming
  • Data Analysis and Evaluation

STRENGTHS

  • Problem Solving
  • Quick Learner and Go-Getter
  • Collaborative work
  • Discipline and accept Challenges
  • Team Player
  • Recognized as a subject matter expert in AI, invited to share insights and knowledge with diverse audiences, including post graduate students.
  • Mentor

Awards

Gold Medal in Master of Technology, Best Project in Master of Technology

Publications

  • ACM Journal 1-2021
  • ACM Journal 2-2021
  • Detection and Tracking of Text from Video Using MSER and SIFT, (Book Chapter) Advances in Decision Sciences, Image Processing, Security and Computer Vision, Springer, 2020.
  • Springer Book Chapter-1 2020

Timeline

Data Scientist

Ascent Fund Services
11.2021 - 08.2024

Data Scientist

KBC Bank en Verzekeringen
03.2021 - 08.2021

Junior Data Scientist

BeCode.org
10.2019 - 03.2021

Assistant Professor

VNR VJIET
10.2008 - 07.2019

Doctor of Philosophy (PhD) - Computer Vision and AI

Jawaharlal Nehru Technological University

Master of Technology - SE

Jawaharlal Nehru Technological University

Bachelor of Technology - CSE

Jawaharlal Nehru Technological University
Dr. MANASA NOOLU PhD