Aarthi Shankar
Scan contact card
An aspiring Data Scientist and an experienced Software Engineer with a willingness to constantly learn, code and play around with data. Skilled in Statistical Data Analysis, Machine Leaning, Python, R, MATLAB and Java.
Skills
- Java
- Android
- C ++
- C
- Shell Scripting (bash)
- R
- Python
- Matlab
- HTML5
- CSS3
- JavaScript
- JQuery
- PHP
- JSP
- Oracle
- MySQL
- SQLite
- Microsoft Access
- Weka
- Microsoft Office (Word, Excel, Access, Power Point)
- Tableau
- R Studio
- Power BI
- Google Analytics
- Enterprise Architect
Creations
A collection of projects authored by Aarthi, and likely shared out with the community as an open source project.
Breast Cancer Risk Prediction
Using a labelled data set (Wisconsin breast cancer diagnostic data) of cancer patients and the various attributes of a cell such as radius, texture, area, perimeter etc, a model was trained to predict the possibility of a cell being cancerous using Logistic Regression and K-fold cross validation.
Crime Rate prediction using K-Means
Analysed the San Francisco crime database using the K-Means clustering algorithm, to predict the most crime-prone neighbourhoods.
Pedestrian-Vehicle Interaction detection
Real-time surveillance video from traffic cameras was taken as an input, and was split into frames. An algorithm was designed to extract HOG and GLCM features from the images and classify using Multi-Class Support Vector Machines and Parallel Algorithms. This trained model was used to detect pedestrian-vehicle interaction.
Wait! There's more..
See all Creations for more details!
Publications
A collection of papers or presentations authored by Aarthi.
Paper - Redesigning the Application Development Process of Champaign-Urbana Mass Transit District
Paper - TRANSPR - Transforming Public Accountability through Block-Chain Technology
Experience
Research Assistant
Formulated algorithms to perform textual analysis on a large dataset of emails and to obscure Personally Identifiable Information in the dataset. Exported the manually trained (tagged as public or restricted) items from one tool to another using VLOOKUP based on date and time as the key to match the document id across two tools to save time from manually training the tool and tagging again. Analyzed and evaluated multiple text analysis tools like Advance eDiscovery, ePADD, Recommind which use Machine Learning and predictive analysis for detecting sensitive data.
Software Engineer
Designed and developed a feature that enhanced the data-type support in message attributes. Developed a distributed state machine spanning across systems - Nokia Access Virtualizer and Access Management system, to monitor and notify the counterpart on state changes. Ensured the ahead-of-time delivery of this critical piece in a major customer requested feature. Fixed a number of bugs and made enhancements for inclusion in future code releases and patches
Data Analyst Intern
Analyzed user behaviour on various platforms and generated reports for product development. Built a dashboard to consolidate analytics data from various sources.