I am Akshara Santharam, currently pursuing Masters in Computer Science from SUNY Buffalo. Actively looking for Software Engineering / Data Engineering / Data Analytics full-time roles | Highly motivated and accomplished Computer Science Engineering graduate with experience as a Data Science intern | Well experienced in interpreting and analyzing large volumes of data to drive successful business solutions
-
Experience
Data Science Intern, Intellect Design Arena Ltd., India Jan 2019 – June 2019
• Operated on data annotation initiatives to train the custom-named entity recognizer to facilitate the identification and extraction of domain-specific entities from the advice set documents. (Wealth Management Artefacts).
Software Development Intern, LCube Innovative Solutions Pvt. Ltd., India June 2017
• Developed an Electronic Medical Record (EMR) application for hospital clients using Java Technologies to aid in the management of the patient’s record in a healthcare company.
-
Projects
ACADEMIC PROJECTS
Breast Cancer Classification using Logistic Regression
• Wisconsin Diagnostic Breast Cancer dataset was collected from the UCI machine learning repository and trained using Logistic Regression. A machine learning model was built that can classify the cancer cells to Benign and Malignant.
Simple SOLR Based Indexer using Twitter API
• Created a python script which can collect, crawl and process the tweets of personalities from Twitter user timeline using Twitter APIs which can handle duplicate tweets, retweets, and replies and performed indexing of the processed tweets in the SOLR instance according to the requirements like Person of Interest, Language, Country etc.
Search Engine to analyze the Impact of Political Rhetoric in Social Media
• Engineered a search system hosted on AWS cloud using AngularJS and ReactJS that takes data like tweets, replies, retweets from Twitter using Twitter APIs and indexes it in Apache SOLR according to the requirements like Person of Interest, Language, Country etc., to provide relevant results for queries.
• Sentiment analysis are used on the POI’s replies to analyze and visualize the impact of their country’s rhetoric using Kibana.
INDUSTRY PROJECTS
Custom Named Entity Extractor, Intellect Design Arena Ltd. [Python, NLTK, Spacy, HTML, CSS, Flask, Visual Studio Code]
• Built a custom named entity extractor that can be trained using the annotated data to identify and extract domain-specific entities like the name of Financial organization, Government Organization and Transaction amount from the advice set documents.
• Developed a Named Entity Recognition (NER) model that can upload the advice set documents and extract the entities.
Electronic Medical Record application, LCube Innovative Solutions Ltd. [Java, HTML, CSS, JavaScript, Eclipse, PostgreSQL]
• Developed an Electronic Medical Record (EMR) application for a hospital client to aid the patient's records management and appointment scheduling.
PERSONAL PROJECTS
Data Modeling using Apache Cassandra [Python, Apache Cassandra, ETL pipeline, Jupyter Notebook]
• Modeled the data by creating tables in Apace Cassandra to run queries and built an ETL (Extract, Transform and Load) pipeline that transfers data from a set of CSV files within a directory to create a streamlined CSV file to model and insert data into Apache Cassandra tables.
Data Lakes using Apache Spark on Song dataset and Log Dataset [Python, Spark, ETL, AWS, Redshift, Jupyter Notebook]
• Built an ETL (Extract, Transform and Load) pipeline that extracts data from AWS S3 bucket, processes the data into respective tables using Apache Spark, and loads the data back into AWS S3 as Spark parquet files.