Resume

Sign in

Python, Data analysis, abap, sql

Location:
Newark, NJ
Salary:
90000
Posted:
October 12, 2019

Contact this candidate

Resume:

JASON AMITH FERNANDO

adakrd@r.postjobfree.com +1-973-***-**** 234, Harrison Avenue, Harrison, NJ -07029

https://www.linkedin.com/in/jason-fernando-67058b20/ https://github.com/Jason-Amith EDUCATION

New Jersey Institute of Technology, NJ, USA Anticipated graduation - Dec 2019

• Master of Science, Data Science

Courses: Machine Learning, Big Data, Applied Statistics, Deep Learning, Data Structures and Algorithms, Database Management System Design, Data Analytics with Python, Data Analytics for Info Systems, Data Driven Financial Modelling Rajiv Gandhi Institute of Technology, University of Mumbai, Mumbai, India August 2009 - May 2013

• Bachelor of Engineering, Instrumentation Engineering TECHNICAL PROFICIENCY

• Languages: Python, ABAP, SQL, SPL, VBA

• Frameworks/Platforms: Kafka, Spark, Hadoop, SAP BOPF, SAP: ECC, Gateway, HANA, DataHub, AWS EC2

• Libraries/APIs: Tensorflow, Keras, Sci-kit learn, NumPy, Pandas, matplotlib, seaborn, plotly

• Version control: SAP CHARM, Git

• Database: MySQL, MSSQL, Postgres, HDB

• Packages/Tools: SAP CPM, PS, FICO, SD, Tableau, Weka, MS Excel, Anaconda, Splunk Enterprise7.x

• Web frameworks: Django 2.2, Flask

EXPERIENCE

Forbes Sep 2019 – present

Data Science Intern/Capstone

• Carried out applied data science methods for Image and Title Analysis for Article optimization, in Python, leveraging GCP.

• Collected, pre-processed and annotated text and image data, using python, pandas and Google Vision API, followed by applying statistical and machine learning models to predict the performance of articles, using scikit-learn.

• Performed model validation and feature engineering to correlate article’s features with high page views, followed by extracting actionable insights to inform business decisions.

IBM Dec 2014 - Jul 2018

SAP ABAP Developer/ Technical Consultant

• Designed and implemented SAP ECC applications for EY’s ERP, considerably reducing operational costs in Finance & Controlling, Commercial Project Management, Billing, Service Delivery and Administration and Human Capital Management.

• Developed and improved performance of transactional apps, batch jobs, interactive ALV reports and Adobe forms. Enhanced standard modules and made customizations using BADIs and implicit enhancements using OO-ABAP for FI/CO, HR and Billing.

• Built and supported CPM/PS applications using BOPF. Developed extensive REST APIs in SAP Gateway.

• Performed data transfers using BDC, LSMW, ALE/EDI Idocs. Built an ETL pipeline with BODS using BAPIs.

• Implemented CDS views and exposed its Odata artefacts for Fiori consumption.

• Developed all RICEFs in ECC 6.0, EHP8 SP12 on SAP NetWeaver 7.4, S4HANA OnPrem 1709 and SAP HANA Studio. PROJECTS

ML_NLP_DA (Python, Flask) July 2019 - present

• Implemented ML models as REST APIs using Flask, NLP-text and financial data analytics using NLTK and pandas respectively. Data-Visualization-with-Python (Python) Jun 2019 - present

• Implemented libraries such as matplotlib, seaborn, folium and plotly, to display immigration dynamics of Canada by citizenship. DataHub Pipelining (SAP DataHub, Docker, Apache kafka) Jun 2019

• Implemented a data pipeline in a dockerised environment wherein sensor data is written into a Kafka message queue, the same is then read, converted and displayed on a terminal.

Deep-Learning-NNs (Python) Jan 2019 - May 2019

• Implemented a Single layer convolutional neural network(SLNN) with sigmoid activation using Numpy, Stochaistic Gradient descent(SGD), Mini-batch SGD, SLNN training from scratch, created convolutional neural networks(CNNs) with transfer learning, to classify Kaggle datasets such as fruits-360, flowers and chest_xray. The constraint being 90% accuracy. Machine learning algorithms (Python) Oct 2018 - Dec 2018

• Implemented supervised machine learning algorithms, in Python. Some of the implemented classifiers are: Naive Bayes Classifier, SVM and logistic discriminator, using datasets from the UCI machine learning repository, the constraint being 80% accuracy.



Contact this candidate