Data Scientist

ARPIT SHAH

**** *. *** ****** *** H, Bloomington, IN 47408 +1-812-***-**** ********@**.***

LinkedIn: www.linkedin.com/in/shah-arpit

EDUCATION

Indiana University, Bloomington, Indiana August 2018– May 2020 Master of Science in Data Science GPA – 3.53/4

Current Courses:Machine Learning in Signal Processing, Deep Learning, Applied Algorithms, High Performance Big Data Systems, Advanced Database Concepts, Introduction to Statistics. KJ Somaiya College of Engineering, Mumbai, India June 2013 – May 2017 Bachelor of Engineering in Computer Engineering CGPA – 3.5/4 Relevant Courses:Database Management and Systems, Data Warehousing and Mining, Distributed Databases, Data structures. TECHNICAL SKILLS

● Programming Languages:Python, R, C#, Java, C++, C

● Web Technologies:AngularJs, JavaScript, HTML, CSS

● Database:SQL server, Postgresql, Oracle

● Certifications: OCPJP (Oracle Certified Java Programmer), Big Data Analytics and Machine Learning affiliated to MIT FabLabs WORK EXPERIENCE

Indiana University, Bloomington, Indiana January 2019 - Present SQL Server Developer

● Working with a large database containing Census, American Community Survey, and other demographic data to build out different indices that factor in to disaster resilience. GEP Worldwide, Mumbai, India June 2017 – June 2018 Associate Software Engineer

● Developed APIs and Stored Procedures along with Middleware for ease of user usability and data retrieval for the website.

● Utilized ElasticSearch to improve performance of search system of the product. Alchemus Infotech LLP, Mumbai, India December 2015 – March 2016 Assistant Engineer

● Stored content for website in form of quotes, images, videos, audio files for the website using MongoDb.

● Collaborated with Search Engine Optimization team and also filtered the content to be uploaded on the website. ACADEMIC PROJECTS

Audio Sentiment Analysis Python August 2018 - Present

● Performed speaker diarization on audio files of conversation between a customer and call center agent to separate out customer’s audio from the whole conversation.

● Developed a Deep Neural Network which was trained on acoustic features of audio files from RAVDESS dataset.

● Extracted acoustic features such as Mel-frequency cepstral coefficients (MFCCs), STFT, Mel Spectrum, Contrast, Tonnez and Chroma from customer’s audio and fed this features to the network to classify the sentiment of the customer. Prediction of Diabetes R June 2016 – May 2018

● Designed and developed an android application that took parameters such as BMI, Age, Blood Pressure, etc. as input to predict if a person is diabetic or not.

● Calculated the weights of the network using Adaptive Neuro-Fuzzy Inference System (ANFIS) in R and used them in backend of the application to predict if the user had diabetes or not. Workload Classification R September 2016

● Classified workload on a soldier at the time of war in terms of the 3 classes- Baseline (BL), Low Workload (LWL) and High Workload (HWL) using the DRDO (Defense Research and Development Organization) Dataset.

● Calculated accuracy of each model using Neural Networks and Support Vector Machines (SVMs). Forecasting Sales Data Excel September 2016

● Analyzed data set acquired from Red Hat to identify and forecast sales trends to predict the desired profitable outcome.

● Utilized moving average, exponential smoothing, regression and residual methods to select a tentative profitable plan. EXTRA CURRICULAR ACTIVITIES

Indy Big Data Visualization Challenge, Indianapolis, Indiana September 2018

● Identified various challenges that Indiana state could face to fill 1 million jobs in next 10 years. Leo Club of Bombay Mulund Youth (NGO), Mumbai, India June 2017 – June 2018

● Event head for conducting knowledgeable sessions and fun games in lower income areas.

Contact this candidate