About Me
I am currently studying my Master's in Computational Science with specialization in Data Science at San Diego State University. I like working with numbers and working with people. The similarity between the two? They are both about stories. Numbers tell us stories. Numbers record the history and project the trajectory of an event. With stories, numbers become comprehensible and friendly. People are full of stories, each of which is unique. When we try our best to understand each other's stories and motivations, communication and collaboration become easy and effective. As for pursuing a career as a data scientist, I believe in the power of storytelling. I want to successfully translate numbers into stories for different types of audience. To me, data science is about discovering the story behind each number. Because, behind every ripple, there is an act. In fact, I wanna be part of the team for finding sustainable and efficient solutions to the real world complex issues
Work Experience
Machine Learning Intern
Creating a classification based system for community associations to store, share, and retrieve property-related records to enable more accurate forecasts for budgeting purposes
Achievements:
- Trained a neural network on 5000 images to classify images into Remaining Useful Life Categories with less than 10% error.
- Implemented Feature Engineering Process like: Standardization and normalization, Encoding categorical variables, and Dimensionality reduction
- Worked on Azure Machine Learning Studio using NVIDIA Tesla K80 GPU to parallelize the processing
Technologies used:
- Python
- Keras
- Tensorflow
- Scikit-learn
- Pandas
- CUDA
- Convolutional Neural Networks
Graduate Assistant
Working in one of the 16 Language Acquisition and Resource Center labs of the USA
Achievements
- Developed an Inventory Management application using which student and professors can gain access to the large collection of resources available at LARC
- Deploy In-House Gitlab services for version control
- Worked on the Statistical Analysis of words and root-attributes of essays of different cohorts using Natural Language Processing
- Created Python Script to perform data definition and data manipulation using DataFrame Objects
Technologies used:
- Python
- NLTPK
- Pandas
- Numpy
- Corpus Libraries
- MySQL
- Microsoft Access
Software Developer Intern
Worked as Intern of two projects- using JSync and Bug Tracking Dashboard
- JSync - Worked mainly on socket programming, concurrency issues and application design, with focus on compressing/decompressing large directories using parallel compression-streams and sending/receiving them serially over a socket stream.
- Sped the file transfer process by 8 times after developing a platform independent version control application
- Bug Tracking Dashboard - Worked mainly on front-end design, client & server side scripting and statistical analysis. Main focus was on developing queries to access their quality tracking database and provide information that could help each team track their weekly, quarterly, and yearly performance for all customers and highlight important/delayed bug-fixes
- Created and launched an analytic web page, which measured and increased the performance of the team by 200%
Technologies used:
- JAVA
- Node.js
- D3.js
- SQL
- Python
- Visualization
- Analytics
Skills & Tools
Languages
-
JAVA
-
Python
-
C++
-
C
-
SQL
-
R
-
MATLAB
Machine Learning Tools
- Tableau
- Keras
- Tensorflow
- Theano
- Caffe
- SciPy
- Pandas
- Scikit-Learn
Others
- Time Series Analysis
- Regression
- Classification
- Computer Vision
- Git
- CUDA
- OpenMP
- MPI
Education
-
MS in Computational Science: Data ScienceSan Diego State UniversityCGPA: 3.92017 - 2019
-
BTech in Information Technology: Data ScienceManipal UniversityCGPA: 3.12013 - 2017
Language
- English (Professional)
- Hindi (Native)
- French (Basic)
Interests
- Guitar
- Photography
- Cooking
- Travelling