D Chelamalasetty

Dallas,TX

Summary

Certified Data Science professional with over 14 years of IT experience. Proven analytical acumen, leadership capabilities, and exemplary time management and communication skills.

Overview

years of professional experience

Work History

AIML Intern

Copart Inc

Dallas

01.2023 - Current

Retrained Deep Neural Network image recognition models for vehicle damage scoring on four corners using CNN and transfer learning, achieving an AUC of 0.89, achieving 20% improvement
Implemented augmentation, Hyper opt, callbacks, class weights, and gradient clipping techniques to achieve a 30% reduction in overall model loss
Optimized model performance through quantization and parallelization techniques, achieving a 20% runtime improvement
Enhanced OTL classification model using GBM by integrating scores from Deep NN Model, resulting a 6% AUC improvement
Implemented new Pro-quote model for the DE team, utilizing GBM to anticipate the price quotation (Estimated Sale Price in Auction) for a
Lot, and able to achieve Mean cross-validation score to 88%, with RMSE 1232.25 through data preprocessing, feature engineering, and hyper-parameter tuning which resulted in 2% improvement of existing US PQ Model
Created Tableau dashboards to offer insights into PQ and Damage score models.

Technical Member

Dallas

12.2022 - Current

Mentor

BALC

05.2022 - Current

Solution Architect

Huawei Technologies

04.2008 - 08.2021

Collaborated on in-depth research and workshops with Architects, driving the design and delivery of establishing Recommendation systems in APAC region, for different Ad, Video and Music Apps, resulting in serving 0.4 million users per day
Collaborated with Data Scientists and Business teams to enhance models such as FTRL, LR, SVD, Cosine Similarity, and Collaborative
Filtering
Successfully boosted p-CTR by 5% across various Ad and video types, achieving an AUC of 82%
Engineered and optimized custom ETL data pipelines for ML model sources using HIVEQL and PYSPARK, enhancing data quality by through comprehensive dataset analysis
Designed and deployed robust ETL data pipelines, transitioning data across ODS, DIM, DW, and ADS layers to introduce self-analytics and reporting functionalities
Effectively developed and transitioned over 400 HIVEQL reports within the Business Intelligence platform
Directed the requirement gathering and analysis phases, transforming insights into BRD/FRS documentation
Managed and executed customizations and migrations for OSS/BSS product enhancements, benefiting over 40 global telecom operators
Stack Exchange Questions April 2023
Preprocessed data with spaCy, including lemmatization and stop word removal, Employed Genism’s Word2Vec for embedding generation
Tested models including One Vs
All classifiers and Neural Networks achieved an F1-score of 0.84
Deep Learning Hackathon December 2022
Achieved first place in an in-class Kaggle competition by ensemble various transfer learning deep learning models, attaining a 98.2% acc
Crescent Bank Hackathon
Constructed a GLS model to forecast recovery rate/BAD, achieving an RMSE of 0.2 and an adjusted R^2 of 94%.

Education

Master of Science - Business Analytics

University of Texas

Bachelor of Technology - Electronics & Communications

Nagarjuna University

Skills

TECHNICAL SKILLS:
Analytics Tools : Python, Py-Spark, SPARKSQL, R, STATA, SQL, HIVEQL, Solver, VBA macros, Alteryx, NumPy, Pandas
Frameworks : PyTorch, FASTAI, Scikit-Learn, H2O, Open CV, Tensor Flow, Kera’s, Spacy, Glove, Word2vec, Genism
Database : Hive, Mongo DB, HDFS, MySQL, Single Store, BQ

Visualization Tools: Tableau, MS Excel
Analysis : Hypothesis testing, ANOVA, Chi-square, Statistical modeling, t-test, Time-series, Ad hoc data analysis
Soft Skills : Problem-Solving, Teamwork, Communication, Leadership, Adaptability, Collaboration, Creativity, Multitasking

Accomplishments

Certifications : AIML, Generative AI, Tableau, SQL, R, Alteryx

Timeline