About Me

Hello, I am a graduate student at Santa Clara University, CA pusuing MSc in Computer science with focus on Data Science. I am also an online course learning enthusiast and have completed several courses, which I will be mentioning below.
In the past I have worked as software engineer handling all phases of SDLC life cycle for an application used to send out notifications to customers on paper, mail, SMS, Swift etc.
Apart from this I work on campus as Sports official at Santa Clara University and I am a Team member in the SWE(Society of Women Engineers) organization.

Contact Details

Arpita K.A. Singh
2147 Newhall Street, Apt #221,
Santa Clara, CA 95050 US
+1 (669) 210-4727
asingh6@scu.edu

Download Resume

Education

Santa Clara University, CA

Master's of Science in Computer Science • Expected March 2019

Currently pursuing MSc in CSE by taking subjects like : Algorithms: Design & Analysis, Database Systems, Software Developement & Process Management, Natural Language & Processing, Operating Systems, Pattern Recognition & Data Mining, Software Ethics, Artificial Intelligence.

Visvesvaraiah Technological University, India

Bachelor's of Science in Information Science • July 2010

Graduated in 2010 by taking subjects like Data Structures, Algorithms, Software Engineering.

Work

Gofind.ai

Machine Learning Intern • May 2018 - Present

• Primary task includes building a product recommendation model using ‘Bag Of Words’ Model for text similarity, TF-IDF and Word2vec for product similarity, and then CNN based image features for product similarity.
• Recommending attire suggestions to the users based on their current choice.
• Collect and modify the data like removing similar titles, missing data, duplicate data among a few.

Larsen & Toubro Infotech Ltd.

Software Engineer • February 2011 - September 2017

Awarded ACE – Best Team award in 2014 and 2015
• Acted as application owner/Subject matter expert for an invoicing system handling all phases of SDLC lifecycle from requirement gathering, analysis, High Level/Detail Level Design, Code, unit testing, QA testing, production implementation and providing level 1 support.
• Data generation, analysis and cleaning to predict system and user requirements by refining existing technical architectural and Database operations such as Creating/managing objects like Table, Indexes, Functions, Sequences, Users, and Table-space – Database optimizations.
• Data remodeling received from mainframe systems, restructuring and data manipulation to send it to Message Plus/Open tool via https requests to collect more information and then send it to word processing tools like MS Word to further format it.

Skills

Languages/Web Framework/Libraries/Tools:
Python, Java, HTML5, CSS3, JavaScript, XML, XSLT, Django, Tkinter, DB2, Oracle 11g, MongoDB, MySQL, NoSQL, Bootstrap, Eclipse, Netbeans, Android Studio, GitHub, TensorFlow, MATLAB, NLTK, Scipy Stack: numpy, scipy and pandas, Gensim, Scikit-Learn, PyCharm CE, MatplotLib.

Python
Java
SQL
MongoDB
HTML5
CSS

Check Out Some of My Projects.

Factoid based Question Answer System

Implemented a chat bot for natural language question-answering, summarization and dialogue management in Python using seq2seq neural machine translation model of TensorFlow, NLTK and SQLite

Nordea Bank AB - Migration Project

Migration project from COBOL to MPO, of invoicing system.

Fake News Detection

Considered two measurements to leverage fake news detection. They are stance detection from Fake News Challenge (FNC). Applied feature engineering like count the n-grams, calculate the TF-IDF of the headline and body, applied Singular-Value Decomposition to obtain a compact, dense vector representation of the headline and body and then Absurdity feature is implemented by using Part of Speech(PoS) tagger and Named Entity Recognizer (NER) from NLTK toolkit.

Yelp kind Database

Built a JAVA application which runs queries on Yelp data and extracts useful information. The user can filter the search results using available business attributes. For this designed a conceptual schema using the (E)ER Data model. Converted the EER schema to tables and then implemented these tables in the Oracle database. Use dataset in JSON to get the data.

Analysis of MapReduce Staggering problem

MapReduce has staggering problem and several solutions are available for the same. Analysed one of them.

Broadcasting-in-ad-hoc-network

Reliable broadcasting in mobile ad-hoc networks

I'm Arpita K.A. Singh.

A San Francisco based MSc in Data Science student, with 6 years of experience as Software Engineer based out of Copenhagen, Denmark and Mumbai, India. Let's start scrolling and learn more about me.