| | | 20,000+ Fresh Resumes Monthly | |
|
|
| |
Click here or scroll down to respond to this candidateCandidate's Name , Ph.D.Billerica, MA Street Address PHONE NUMBER AVAILABLEEMAIL AVAILABLE https://LINKEDIN LINK AVAILABLEPROFESSIONAL SUMMARYSkilled data scientist proficient in Artificial Intelligence/Machine Learning and SQL, leveraging machine learning models and statistics expertise to achieve business goals by uncovering insights, optimizing, and improving the efficiency of processes. Skilled in analyzing, visualizing, and modeling real-world data through multiple hands-on projects.TECHNICAL SKILLSMachine Learning Data Mining Data Visualization Data Analytics Data Processing Feature Engineering Data Modeling Statistical Analysis Regression Classification Clustering Ensemble methods Oversampling / Under sampling Techniques Hyperparameter Tuning Model Evaluation Dashboards Project Management Python SQL R NumPy Pandas Matplotlib Scikit-learn SciPy Seaborn SQL Server SSMS SSIS IBM Db2 Apache Zeppelin Jupyter Notebook Google Colab IBM Watson Studio IBM Cloud Azure DevOps Server Jenkins Tableau GitHubKEY PROJECTS IN MACHINE LEARNINGProject: Credit Card Users Churn PredictionBuild a classification model to help the bank identify customers who will leave their credit card services and identify the reasons for renouncing their credit cards so that the bank can improve its services and stop leaving.Identified which customer attributes are most significant in identifying this cause.Skills and tools: EDA Data Preprocessing Missing Value Treatment Identify Multicollinearity Outlier Treatment Decision Trees AdaBoostClassifier GradientBoostingClassifier RandomForestClassifier BaggingClassifier XGBClassifier Over Sampling Under Sampling Hyperparameter Tuning Business RecommendationsProject: Personal Loan Campaign ModelingAnalyzed and built a decision tree model that will help the marketing department to identify the potential liability customers who have a higher probability of purchasing a loan and becoming an asset customer.Identified which customer attributes are most significant in driving purchases and identified which segment of customers to target more.Skills and tools: EDA Data Preprocessing Missing Value Treatment Decision Trees pre-pruning post-pruning Business RecommendationsView my projects on github.View my ePortfolio for Artificial Intelligence and Machine Learning Projects - Postgraduate Program in AI and Machine Learning: Business Applications, UT Austin McCombs School of Business.PROFESSIONAL EXPERIENCESQL Developer/Applications, kSARIA Interconnect, Hudson, NH 11/2023 01/2024Created and modified SQL database(s) and managed multiple database engines for storing, processing, and securing data.Managed and modified database objects, including tables, views, and stored procedures, and verified their functionality - created and modified visibility reports using IQPlus Designer.Imported/exported data from one location to another using the import and export wizard in SSMS.Ran SSIS jobs via Visual Studio to extract and transform data from various sources, such as XML files, flat files, and relational data sources, and loaded data into one or more destinations.Handled SQL Server Data Tools (SSDT) and SSIS Toolbox features to create new SSIS packages and execute specific ETL tasks - deployed databases to their respective server environments (Azure DevOps Server).Scheduled and automated database and server administration tasks using SQL Server Agent and monitored server activities through logs.SQL Analyst, Apple via RMSI North America Inc, Sunnyvale, CA 09/2022 04/2023Designed and monitored automated workflows for Apple Maps using SQL and Python scripts and applied manual interventions to ensure source data was adequately staged and ready to use.Integrated data from several datasets written in JSON format (semi-structured) into a single database.Performed data cleaning and wrangling to convert data into usable formats.Implemented various data mining techniques, generated reports using Python packages like Pandas, Matplotlib, and NumPy, and edited the weekly report according to business requirements.Performed visualizations on the Tableau dashboard and shared reports via the Tableau server to communicate the insights to project stakeholders, peer groups, and team members.Reviewed codes using notebook sharing or GitHub pull requests and helped improve the code quality.Conducted meetings with peer groups and team members to discuss the project targets and implemented goal-oriented strategies.Created weekly radars for project updates and modified and maintained quip documents for new trainees.CERTIFICATESPost Graduate Program in AI & ML: Business Applications, McCombs School of Business, UT Austin PresentProject: FoodHub ProjectPerform an exploratory data analysis and provide actionable insights for a food aggregator company to understand the demand for different restaurants and cuisines. This will help them enhance their customer experience and improve their business.Identified which attributes are most significant in driving purchases and identified which segment of customers to target more.Skills and tools: Python Numpy Pandas Seaborn Univariate analysis Bivariate analysis Exploratory Data Analysis Business RecommendationsIBM Data Science Professional Certificate, IBM (via Coursera), Remote 2022Project: Applied Data Science Capstone ProjectPredicted success of SpaceX Falcon 9 rocket landing following data collection from SpaceX Rest API and web scraping HTML tables.Performed data wrangling, exploratory data analysis, and interactive analytics.Applied machine learning algorithms to model the success of the SpaceX Falcon9 landing (Logistic Regression, Support Vector Machine (SVM), Decision Tree Classifier, and K Nearest Neighbor (KNN)).Utilized Python, SQL, Folium, Dashboard, and Machine learning algorithms.Project: Real Estate Investment Trust ProjectPerformed exploratory data analysis using the Seaborn library in Python to identify general patterns in house sales.Implemented a multiple linear regression model to predict the market value of house sales in King County, Washington, based on a given set of features. Utilized Python and machine learning algorithms.Business Intelligence with Tableau, EDUCBA, Remote 2022Customer Analytics using Tableau and R, EDUCBA, Remote 2022Biostatistics in Public Health Specialization, Johns Hopkins University (via Coursera) 2021 - PresentRESEARCH EXPERIENCEPh.D. Student Researcher/ Data Analyst, The University of Texas at Dallas 01/2015 05/2020Project: Multivariate Statistical Analysis of Hydrothermal and Cold-Seep Vents in the Mariana Convergent Margin: Tectonics, Fluid Chemistry, and Biology.Compiled a database for Mariana convergent margin cold seeps and hydrothermal vents and integrated diverse datasets into a single database.Performed data cleaning and preprocessing and then implemented exploratory data analysis to visualize general trends in the data using the ggplot2 (Tidyverse) data visualization package in R.Utilized nonparametric statistical procedures to analyze relationships between variables and identified correlations between fluid parameters vs depth, temperature, and chlorinity. Kendalls tau coefficient was calculated for each relationship.Compared the vent parameters of different tectonic segments using rank-based non-parametric Analysis of Variance (ANOVA) and discovered some significant differences in fluid parameters.Analyzed similarity among vent biota using the Srensen similarity coefficient at their species and genus levels. Utilized R programming language, Advanced ExcelProject: Global Mid Ocean Ridge Hydrothermal Vents and Their BiotaUtilized nonparametric statistical procedures to analyze relationships between mid-ocean ridge and Mariana convergent margin vent systems.Compiled a database for 449 individual hydrothermal vents grouped into 73 vent fields and performed data cleaning, preprocessing, and statistical analysis.Implemented exploratory data analysis to visualize general trends in the data using the ggplot2 (Tidyverse).Compared the vent parameters using rank-based non-parametric Analysis of Variance (ANOVA) and discovered some significant differences in fluid parameters.Analyzed similarity among vent biota using the Srensen similarity coefficient at their species and genus levels. Utilized R programming language, Advanced ExcelEDUCATIONPh.D. in Geosciences, The University of Texas at Dallas, TX 2020MS in Geosciences, The University of Texas at Dallas, TX 2017B.Sc. in Geology, University of Peradeniya, Sri Lanka 2011 |
