Girma Ayana

• Data transformation (Extract-Transform-Load), data migration and storage on premises and AWS (S3 V2), and data warehousing on AWS Redshift using tools such as SQL-SISIS, and Informatica Intelligent Cloud (IIC).
• Developed custom data analytics solutions, leading to improved operational performance and strategic planning using R, Python, SAS, and SQL (SSAS, SSRS) for clients.
• Data reporting, dashboarding, and business intelligence using SQL tools, Tableau, and Power BI tools.
• Automate repetitive tasks using scripting languages such as Python or R, saving time during the analytical process significantly.
• API development, get/post data from several sources using API and database tools.
• Preparing data pipelines, data libraries, and standard code documentation.
• Evaluated emerging technologies to assess potential applications within the organization''s existing infrastructure or future projects.

• Formulated breeding objectives and leveraged interdisciplinary approaches in genetics and data science to innovate crop varieties with superior traits.
• Managed statistical designs and analytics for research across varying conditions, trait heritability estimation, and enhancing line/hybrid selection through genotype-environment (GxE) analysis.
• Performed advanced genetic analyses across (bi-parental mapping, GWAS, etc.) four crops, identifying patent-pending markers/QTLs in stevia and implementing gene mapping and association studies.
• Developed genomic selection models using AI and machine learning, achieving significant prediction accuracy mainly for qualitative traits and cost reduction across five crops.
• Optimized genomic selection strategies for time and cost efficiency in the South Dakota State University oat breeding program.
• Proficient in predictive modeling and analysis using a suite of software tools, including JMP genomics, several R packages and in-house coding, Python modules (PyTorch, TensorFlow, Keras, Scikit-learn, Pandas, NumPy, SciPy, Matplotlib, etc.), and SAS.

• Developed and deployed predictive models using machine learning algorithms, choosing the most accurate ones. Utilized R, R-Shiny, R-Markdown, and Python.
• Supported PI with research design review, protocol preparation, literature reviews, and case studies varies research projects and initiatives.
• Engaged in data collection and integration, analyzing spatial and temporal data, testing hypotheses, and presenting results to varied audiences.
• Assisted the research in visualizing, publishing, and communicating findings.
• 
  

Data Science Project:

• Created models for predicting credit default and conducted data-driven customer segmentation using various techniques, including logistic regression, decision trees, random forest, boosting, Naive Bayes, KNN, SVM, MARS, and unsupervised learning methods.

• Directed 141 research and administrative staff, project funds, and research activities
• Directed research projects that led to developments of six improved varieties and 41% increase in business performance
• Provided technical leadership about business insights, product profiling and demand projections
• Created statistical analysis plans, design of experiments, hypothesis testing, data management activities, and programming specifications for a wide range of studies
• Conducted organizational skill, technology, and business need analysis
• Auditing business KPI and the work environment to ensure business goals and compliance with legal, health and safety standards.