Bazezew Belayneh — Data Scientist

As a seasoned Data Scientist with over 6 years of experience, I specialize in leveraging advanced data analysis, machine learning, and natural language processing techniques to drive impactful business solutions. My expertise spans a diverse range of industries, including banking and healthcare, where I have consistently delivered complex models and actionable insights. I excel in developing and deploying sophisticated multilabel classification and regression models, as well as deep learning architectures. My hands-on experience in MLOps ensures that models are not only implemented effectively but also maintained and optimized for long-term performance. Additionally, I have utilized Azure and AWS frameworks to enhance the scalability and reliability of data solutions. A key achievement in my career includes creating an EDA Dashboard using the LangChain framework based on OpenAI's GPT-4 LLM. This innovative solution has significantly reduced the time and human resources required for exploratory data analysis, enhancing efficiency and productivity for the team. My career highlights include: - Successfully developing and deploying complex machine learning models to enhance predictive accuracy and operational efficiency. - Implementing robust natural language processing solutions to extract meaningful insights from unstructured data. - Driving innovative solutions in banking and healthcare, addressing critical challenges through data-driven strategies. - Ensuring seamless model deployment and maintenance with comprehensive MLOps frameworks. - Leveraging Azure and AWS frameworks to build scalable, reliable, and efficient data solutions. I am passionate about staying at the forefront of technological advancements and continuously improving processes to deliver superior results. My goal is to leverage my skills and experience to contribute to cutting-edge projects and drive data science innovation.

Stackforce AI infers this person is a Data Scientist specializing in Fintech and Healthcare with strong MLOps and machine learning capabilities.

Location: Silver Spring, Maryland, United States

Experience: 8 yrs 1 mo

Skills

Machine Learning
Data Analysis
Natural Language Processing
Mlops

Career Highlights

Developed complex machine learning models for predictive accuracy.
Implemented NLP solutions for unstructured data insights.
Created an EDA Dashboard using LangChain and GPT-4.

Work Experience

Bank of America

Data Scientist | Machine Learning Engineer (4 yrs 11 mos)

UnitedHealth Group

Data Analyst | Data Scientist (3 yrs 2 mos)

Bazezew Belayneh

Data Scientist

Silver Spring, Maryland, United States8 yrs 1 mo experience

Most Likely To SwitchHighly Stable

Key Highlights

Developed complex machine learning models for predictive accuracy.
Implemented NLP solutions for unstructured data insights.
Created an EDA Dashboard using LangChain and GPT-4.

Stackforce AI infers this person is a Data Scientist specializing in Fintech and Healthcare with strong MLOps and machine learning capabilities.

Contact

Skills

Core Skills

Machine LearningData AnalysisNatural Language ProcessingMlops

Other Skills

Amazon Web Services (AWS)BERTBM25 TF-IDFCommunicationData AnalyticsData MiningDecision SciencesDocker ProductsFeature EngineeringKerasLarge Language Models (LLM)PythonSBERTSQLStatistical Modeling

About

Experience

8 yrs 1 mo

Total Experience

4 yrs

Average Tenure

4 yrs 11 mos

Current Experience

Bank of america

Data Scientist | Machine Learning Engineer

Jun 2021 – Present · 4 yrs 11 mos

Responsible for developing models, prediction algorithms, and solutions to prescriptive analytics, data mining techniques, and econometric models.
Apply different machine learning algorithms/methods to data to predict credit risk, fraud detection, customer churn, and target marketing.
Communicate results with the operations team to make the best decisions and collect data needs and requirements by interacting with other departments.
Created a search engine using the BM25 TF-IDF Algorithm that uses EMR Serverless for ad-hoc processing of a large amount of unstructured textual data using the BERT and SBERT large language models (LLMs).
Gather and define business requirements and determine datasets for analysis, clarify, format, clean, and manipulate the data and metadata for exploratory and statistical data analysis.
Engineered data features with Python and SQL and used data imputation techniques to resolve missing dataset values.
Utilized Python-based data science packages: Matplotlib and NumPy, using Pandas, Scikit-learn, SciPy, Seaborn,
Brought business insight in rating tables, prediction explanations, and multicollinearity reduction VIF.
Used data validation techniques to validate critical data elements and identify anomalies.

Machine LearningData MiningNatural Language ProcessingPythonSQLBERT+2

Unitedhealth group

Data Analyst | Data Scientist

Apr 2018 – Jun 2021 · 3 yrs 2 mos

Continuous integration and delivery (CI/CD) service for machine learning (MLOPS) and managing machine learning lifecycle with MLflow, Docker, Airflow, and Amazon SageMaker.
Application of various Artificial Intelligence (AI) machine learning algorithms and statistical modelings like decision text analytics, Natural Language Processing (NLP), and Supervised and Unsupervised Regression models.
Collaborated with data engineers and the operation team to implement the ETL process and wrote and optimized SQL queries to perform data extraction to fit the analytical requirements.
Experiment and build predictive models, including ensemble methods such as Gradient boosting trees and Neural Networks by Keras and TensorFlow to predict transaction amounts.
Perform univariate and multivariate analysis on the data to identify any underlying patterns and associations between variables. Then, through the Distributed Cross-Validation process, hyper-parameter tuning is performed.
Analyzed large datasets, applied machine learning techniques, and developed predictive and statical models, developing and enhancing statistical models by leveraging best algorithms
Perform analysis such as regression analysis, logistic regression, discriminant analysis cluster analysis in SQL and Python to improve the delivery of healthcare services and patient outcomes.
Implement model performance evaluation with RMSE, MAE, F-Score, ROC, and AUC metrics.
Build several workflows that combined data preprocessing steps with feature engineering, feature selections, model selections, hyperparameter tuning, model stacking, blending, using cross-validation to avoid overfitting, validating models with lift charts, AUCPR, and ROC curves,
Explaining insights through feature importance analysis and partial dependency plots. Handle class imbalance and large datasets explored the human-machine approach.