Summary
Around 2 year of experience in the field of business intelligence & data science with good understanding of Data and Machine Learning Algorithms, currently working as Data Scientist at BDB Technologies Pvt Ltd. Proficient in Python & have good knowledge of Big Data ecosystem.
Experience
Software Engineer | BDB Technologies Pvt Ltd
Nov 2018 – Present
Project: Logo Detection and Screen Time Analysis Modules & Concepts: CNN, Faster R-CNN, opencv, tensorflow, InceptionV3, transfer learning.
- Detection of logos using object detection through tensorflow.
- Calculating screen visibility time for brand logos.
- Developed scripts to autogenerate labeled data for object detection training.
- Developing end to end object detection pipeline for training other object detection models..
Project: Platform Capability Development Natural Language Processing. Modules & Concept: nltk, Spacy, gensim, LDA, TF-IDF, HMM, TextRank, Word2vec, Polyglot, Soundex, Metaphones, faker
- Developed end to end text pipelines for NLP
- Data Cleaning: Address correction, Search and Cluster correction using (key collision and Distance Methods), Date formate corrections
- Data Masking: Identifying Person Identification Information, Data Anonymization, pseudonymization, Dynamic Masking, Masking by Substitution, Data Redaction.
- Text Pre Processing: Sentence Tokenization, Word Tokenization, Part of speech (POS), Stop-words Removal, Stemming, Lemmatization
- Information Extraction: Named Entity Recognition (NER), N-Gram Analysis, Document Similarity, Document Summarization, Keyword Extraction
- Advance NLP: Topic Modeling, Text Classification, Word embeddings, Sentiment Analysis.
Associate IT Developer | India Medtronic Pvt Ltd
Project: Post Production Support & Development of Enterprise Data Warehouse (SAP BW 7.4 on SAP HANA).
- Worked on Enterprise Data Warehousing with SAP BW on SAP HANA
- Worked on BW data modeling, data extraction (Generic, LO), and BEx Reporting.
- Involved in Post-Production support that includes monitoring of process chains and data loads, reconstruction and rescheduling chains.
- Monitored daily BW data loads and LO Cockpit Jobs, repeat scheduled the Cockpit jobs when daily uploads were delayed, resolved several issues during data loads.
- Developed InfoSpokes (Open Hub Services) to deliver data to external systems as flat files.
- Developed reports on InfoCubes/MultiProviders using BEx Analyzer/Explorer to facilitate summarization of data.
Education
PG Diploma in Big Data Analytics | Center for Development of Advance Computing
2017 - 2017
- Completed PG Diploma Course in Big Data Analytics with 75.38%
Bachelor of Technology | Guru Gobind Singh Indraprastha University
2012 - 2016
- Completed B. Tech in Computer Science Engineering with 67.36%