Wilkommen! or Welcome to my Skillsire profile. As a Graduate student at SUNY Binghamton, I always believe in having a passion towards statistics and data crunching which proves to be a vital link towards data science and machine learning. I am a certified LSSGBB inclined towards Quality Management and I have covered the core ML algorithms to the best of my abilities by doing mini capstone projects over the summer related to supervised and unsupervised algorithms which makes me feel very motivated to learn even more. In addition to that, I am also passionately following Deep Learning , Natural Language Processing and Computer Vision(CV) related fields.
Apart from the above information, I also possess 4.5 years of work experience as a Senior Quality Assurance Engineer or Sr(QA)Test Analyst at Cognizant having worked for both Retail Consumer Goods(RCG) and Healthcare(HC) clients where my skills and expertise included Selenium, UFT, Functional, Automation, mobile testing(Android) etc. combined with soft skills viz., storytelling to the concerned stakeholders and clients.
At the moment, my versatility in terms of exploring new skills in various areas related to Industrial/Quality/Supply Chain/Data Science/Data Analysis makes me flexible towards any employment opening and not glued to any one specific area.
Starting June 2021, I am actively interested in seeking internship(Spring 2021) or full time job opportunities in the areas of:
-Data Scientist
-Data Analyst
-Machine Learning Engineer
-Industrial Engineering
-Quality Engineering/Quality Assurance/Process Engineer
-Supply Chain/ Supply Chain Analyst
Programming Languages: C, C++, Java, R Studio (ggplot2, caret, tidyverse), SAS, Python (pandas, numpy, scikit, matplotlib, pytorch, Tensor flow) Julia, Hadoop
Tools: Pro-E, CATIA, AutoCAD, Arena, Simio, Fusion360, MS Office (Word, Excel, Power Point & Outlook), Adobe Illustrator, Amplide (AMPL),Tableau, Mathematica, Minitab, IBM SPSS, LaTeX, MS SQL Server/MySQL/NoSQL
My hobbies include reading of novels & autobiographies, following sports, ferro-equinology and learning new languages for communication. Please feel free to reach out to me at: vvijaya3@binghamton.edu or vishnuprasanth22@yahoo.com
-
Experience
Cognizant- Sr(QA)Test Analyst- October 2014- April 2019
•Performed manual and automation testing of an application(s) using UFT and Selenium.
•Practitioner level knowledge on Cucumber, TestNG, JUnit and Mobile testing(Android)
•Prevented defect leakage in UAT and Production(live) environments by covering end-to-end testing business-based scenarios and had the knowledge of SDLC including Agile and Waterfall models.
•Handled a team of 4-8 members at Offshore and 2 onsite employees and provided on-time 100% quality deliverables.
•Worked with tools for functional, automation, requirement management, test data management and defect management like HP QC, ALM, RTC, CQ, RQM, ADPART, JIRA, Selenium, UFT, SoapUI, SQL Server.
•Performed Requirement Analysis, Test Design Artifacts, Test Execution, Defect Logging and shared the Daily Status Report (DSR) to the customer and completed the Test Summary Report (TSR), on subsequent signoffs.
•Performed ad hoc and exploratory testing even when the System Integration Testing (SIT) was performed as per the business requirements to uncover new issues.
•Devised out of the box scenarios for a non-requirement application in a detailed way, to ensure 100% test coverage.
•Organized meetings in the presence of business teams, project manager, IT manager and other development teams at various stages to handle Knowledge Transition (KT), Requirements Review, Test Plan Review and Test Results review.
•Excellent critical and lateral thinking skills to go along with attention to detail.
• Willingness in learning new technologies, understanding them fully, thoroughly before implementing them.
•Identified the defects pro-actively at an early stage thus preventing any major mishap in Live environment.
•Flexible, independent, and adapted to the ad hoc tasks from onshore team, in addition to the daily tasks and having attention to detail on each task based on prioritization.
•Submitted the tasks of every individual resource on Cog 2.0 portal every week to push the metrics on time without any delay.
-
Projects
Improving Forecast in Demand for Outward Transportation(Outbound Logistics) in Supply Chain using Machine Learning(ML) Algorithms(Tools: IBM SPSS|| Python-Jupyter Notebook|| Libraries: numpy, xgboost, matplotlib, randomforestclassifier, sklearn.metrics)
Project descriptionLibraries: numpy, xgboost, matplotlib, randomforestclassifier, sklearn.metrics, svc classifier, pandas, sklearn.ensemble, random, csv, gini_index, keras, keras-sequential, Dense, LSTM
Dependent Variable: Monthly Demand Independent/Predictor Variable(s): Tonnage amount between 12 pairs of source and destination points
-Utilizing the Random Forest Classifier method to achieve an accuracy of about 87.0%
-Utilizing the Random Forest regression method to achieve an accuracy of about 97.0%
-Utilizing Decision Tree algorithm to obtain a performance accuracy of about 62.0%
-Utilizing Linear Kernel Support Vector Machine(SVM) supervised algorithm to have an accuracy predicted based on the F1 score retrieved from the data
-Usage of Gradient(XG) Boost Classifier method to gain a performance of about 80%
-Using K Nearest Neighbors to cluster the demand patterns based on the data obtained between Jan 2015-Aug 2019 and the value of K was found to be 3.
-Hierarchical Clustering unsupervised algorithm was deployed to find out the number of groupings done which are plotted in the form of Dendrogram chart to understand a general demand pattern
-Performed Time Series Forecasting using Long Short Term Memory(LSTM) Deep Learning Algorithm and performed 15 iterations to determine the best RMSE value
-Visualizing the results of the deployed algorithms using matplotlib library and determined that LSTM, Random Forest, Support Vector Machine(SVM) and XG Boost classifier algorithm models are the best methods to use, although SVM and Random Forest are the most dependable methods that could be deployed eventually.
Kaggle Competition: Lyft Motion Prediction for Autonomous Vehicles-Build motion prediction models for self-driving vehicles(Tool: Kaggle-Python Notebook|| Libraries: Pytorch, numpy, pandas, matplotlib, torchvision, l5kit)
Project description:
Predicted the vehicle motions with a pretrained vehicle model by
-Loading the train and test data using the L5kit and pytorch packages
-Visualized the target positions movement with draw_trajectory
-Predicted three possible paths together with the confidence score, by using the specific loss function in the form of negative log likelihood.
-Defined the baseline model and returned three possible trajectories together with confidence score for each trajectory.
-Initialized the model and loaded the pretrained weights by the usage of GPU
-Implemented the training loop, when the train parameter was set to True.
-Finally we implemented the inference to submit to Kaggle when predict parameter was set to True.
-For test, by using