Data Science Intern

SIDDHARTHA BINGI

214-***-**** adhnp6@r.postjobfree.com https://www.linkedin.com/in/siddharthabingi/ GitHub EDUCATION:

The University of Texas at Dallas Master of Science in Business Analytics GPA: 3.95 May 2021 Indian Institute of Technology Ropar, India Bachelor of Tech in Electrical Engineering GPA: 3.2 Dec 2014 CERTIFICATIONS & TECHNICAL SKILLS:

Certifications: SAS - Certified Base Programmer for SAS 9, Gyan Data- Applied Data Analytics using R Programming: C, Python, R, SAS, SQL, Scala

Databases: MySQL, Hadoop

Visualization: Tableau, Python (matplotlib, seaborn), R (ggplot2), Excel, Alteryx Machine Learning: Hypothesis Testing, Linear Regression, Logistic Regression, Decision Tree, Random Forest, KNN, K-means Clustering, SVM, PCA, Ensemble Methods, Neural Networks (ANN, CNN, RNN) BUSINESS EXPERIENCE:

Optimal Solutions Inc, New Jersey – Data Science Intern (USDA Agro) June 2020 – Aug 2020

• Predicted the nutrient value of the soil by building PLS, SVR, and RF models, which was cost and time effective for the farmers. Further, Developed the methods for scatter correction and outlier detection on data and improved the accuracy of the models by 18%

• Results of ML models helped in replacing sensors that reduced cost by 60% and improved the performance by 350%

• Implemented Back propagation neural networks to improve accuracy using data reconstructed (77%) by auto-encoders to remove autocorrelation

• Explored IBM Watson Machine Learning platform for migration of code base repository and for parallel processing HCL Technologies, Chennai, India - Software Developer (Cisco WAAS) Aug 2015 – Oct 2018

• Managed component of Cisco product- AppNav of $10,000, used by hundreds of customers worldwide

• Developed features and debugged 50+ defects/bugs to provide support to critical customer cases and increased customer satisfaction rate from 5.3 to 6.7 out of 10

• Mentored 10 freshers to develop appropriate skills for the benefit of the project and company

• Skills - Routing, Switching, Wireshark, CLI, Perl Scripting, TCP/IP, Automation in Python, Data analysis and reporting in Microsoft Excel

ACADEMIC PROJECTS:

Neural Networks, UTD (PyTorch) Sept 2019 – Ongoing CIFAR-10:

• Implemented Convolution neural network optimized using stochastic gradient descent with Nestero and Kaiming normal initialization achieving 80% accuracy on valid and test datasets

• Also, adapted pretrained VGG16 model and re-trained by modifying/adding layers, transformations to achieve 85% test accuracy

Fashion MNIST:

• Achieved over 90% test accuracy using ANN with LeCunn initialization for the weight and batch normalization

• Adapted a LeNet model and improved the model to achieve 94% test accuracy by hyperparameter tuning such as adjusting convolution window size, learning rate, initialization etc. Global Temperature & Earthquakes - Correlation Analysis - (Tableau) Feb 2020 - Mar 2020

• Performed correlation analysis using Tableau between earthquakes and global temperature

• Created action filters and calculated sets for preparing workbooks with Year-Year, YTD, MTD analysis

• Built dashboards for measures with trend line and reference lines Image Processing, IIT Ropar - (Python, MATLAB, PCA, Feature Engineering) July 2013 – May 2014

• Characterized the sub-surface defects in solids using Principal Component Analysis for feature extraction and Hough transform for edge detection under the guidance of Dr. M. Ravibabu, Assistant Professor, IIT Ropar

• Estimated size and depth of sub-surface defects in CFRP within 8% error margin from features selected from video with 2500 frames of specimen subjected under infrared

ADDITIONAL INFORMATION:

Activities /Community Involvement:

• Captained the Badminton team for Inter-IIT sports meet at IIT Delhi (2010), IIT Kharagpur (2011) and IIT Roorkee (2012) Club Memberships: Data Science Club (UT Dallas), Intelligence Analytics Society (UT Dallas)

Contact this candidate