Clivin John Geju

Clivin John Geju

None
United Arab Emirates
English, Hindi
Volunteer On-site

About Me

Data Science graduate with experience owning the full data value chain including data modeling, analysis, reporting, and ML model deployment. Proficient in Python, SQL, BigQuery, Airflow, Scikit-learn, TensorFlow, PyTorc…

Experience

Research Assistant

University of Texas at Arlington · Arlington, United States of America (USA)
Jan 2025 - May 2025 · 3 months

Owned the entire data value chain for an energy analytics research project, including data logging, modeling, analysis, reporting, and dashboard delivery across 10+ years of ERCOT operational records, directly analogous to product data lifecycle ownership in a consumer platform setting., Supported KPI design and goal setting for operational performance monitoring, working closely with senior stakeholders to define metrics that tracked performance drivers and informed strategic decisions., Applied descriptive, exploratory, and predictive analysis techniques in Python to model energy demand and pricing patterns, achieving 95% forecast accuracy and delivering actionable recommendations to product and business stakeholders., Ingested and processed data from multiple source systems via BigQuery and GCP, developing deep familiarity with source data and its generating systems through systematic data profiling and documentation.

Research Assistant

University of Texas at Arlington
Jan 2025 - May 2025 · 4 months

Owned the entire data value chain for an energy analytics research project, including data logging, modeling, analysis, reporting, and dashboard delivery across 10+ years of ERCOT operational records, directly analogous to product data lifecycle ownership in a consumer platform setting.
Supported KPI design and goal setting for operational performance monitoring, working closely with senior stakeholders to define metrics that tracked performance drivers and informed strategic decisions.
Applied descriptive, exploratory, and predictive analysis techniques in Python to model energy demand and pricing patterns, achieving 95% forecast accuracy and delivering actionable recommendations to product and business stakeholders.
Ingested and processed data from multiple source systems via BigQuery and GCP, developing deep familiarity with source data and its generating systems through systematic data profiling and documentation.

Data Analyst Intern

Cardinality AI · Gaithersburg, United States of America (USA)
Jun 2024 - Jul 2024 · 1 month

Owned the analytical domain for consumer intelligence, working closely with business and product stakeholders to identify important questions answerable with data, delivering actionable insights and recommendations that directly supported data-driven decision-making., Analyzed consumer behavioral data to measure engagement patterns, identify conversion opportunities, and track retention signals across 100K+ customer records, delivering insights that directly informed product and growth strategy., Developed deep familiarity with source consumer data and its generating systems through systematic data profiling, contributing to data model design and maintenance and building reporting frameworks that measured performance and identified key performance drivers., Built and maintained automated Power BI reporting pipelines, reducing stakeholder insight generation time by 30% and improving predictive analytics accuracy by 20% using XGBoost and LightGBM classification models.

Data Analyst Intern

Cardinality AI
Jun 2024 - Jul 2024 · 1 month

Owned the analytical domain for consumer intelligence, working closely with business and product stakeholders to identify important questions answerable with data, delivering actionable insights and recommendations that directly supported data-driven decision-making.
Analyzed consumer behavioral data to measure engagement patterns, identify conversion opportunities, and track retention signals across 100K+ customer records, delivering insights that directly informed product and growth strategy.
Developed deep familiarity with source consumer data and its generating systems through systematic data profiling, contributing to data model design and maintenance and building reporting frameworks that measured performance and identified key performance drivers.
Built and maintained automated Power BI reporting pipelines, reducing stakeholder insight generation time by 30% and improving predictive analytics accuracy by 20% using XGBoost and LightGBM classification models.

Student Intern

GAVS Technologies · Chennai, India
Aug 2022 - Sep 2022 · 1 month

Developed and deployed ML models using TensorFlow, Scikit-learn, and Keras, improving model accuracy by 15% and reducing training time by 20% through systematic feature engineering and hyperparameter tuning. , Engineered data preprocessing pipelines ensuring data integrity and readiness for downstream ML consumption, cutting processing time by 25% and improving model performance by 12%., Communicated complex analytical findings clearly to cross-functional stakeholders, contributing to 95% on-time project delivery.

Student Intern

GAVS Technologies
Aug 2022 - Sep 2022 · 1 month

Developed and deployed ML models using TensorFlow, Scikit-learn, and Keras, improving model accuracy by 15% and reducing training time by 20% through systematic feature engineering and hyperparameter tuning.
Engineered data preprocessing pipelines ensuring data integrity and readiness for downstream ML consumption, cutting processing time by 25% and improving model performance by 12%.
Communicated complex analytical findings clearly to cross-functional stakeholders, contributing to 95% on-time project delivery.

Skills

Excel Google Analytics Java Python A/B Testing Azure Hadoop NumPy PySpark Scala TensorFlow Docker Kafka Kubernetes Power BI Tableau SQL BigQuery Airflow Scikit-learn PyTorch XGBoost LightGBM R C C++ Pandas Feature Engineering Classification Regression Clustering Time-Series Forecasting Predictive Modeling Recommendation Systems LLM Fundamentals NLP Concepts Text Analysis Data Enrichment Automated Decision-Making Multivariate Testing Hypothesis Testing Statistical Significance Testing Experiment Design Descriptive Analysis Exploratory Analysis Inferential Analysis Causal Analysis Predictive Analysis Dimensional Modeling Star Schema Snowflake Schema Medallion Architecture Data Profiling Data Auditing Apache Spark dbt CI/CD Pipelines GitHub Actions AWS (S3 Glue EMR) Google Cloud Platform (BigQuery Dataflow) Matplotlib Seaborn Looker (LookML) Google Data Studio Great Expectations PyDeequ (AWS Deequ) Data Quality Engineering GDPR CCPA Audit-Ready Documentation Git SQLAlchemy Jupyter VS Code CatBoost Keras Hugging Face Transformers
Report this Profile?