Hamzah Al Jabari

• Acquired comprehensive training in data science encompassing Statistical analysis, Data visualization, Machine
Learning (ML), Natural Language Processing (NLP), recommendation systems, and big data technologies.
• Employed advanced data analysis and feature engineering methods to extract valuable insights from a
supermarket’s weekly sales dataset.
• Formulated and executed innovative machine learning models (XGBoost, Random Forest, CatBoost) to predict
supermarket weekly sales, achieving consistent accuracy levels of 95% and above.
• Developed a user-friendly Streamlit program/web page for sales forecasting (Weekly, Monthly, Yearly)

Acquired comprehensive training in data science encompassing statistical analysis, data visualization, machine learning (ML), natural language processing (NLP), recommendation systems, and big data technologies.
Employed advanced data analysis and feature engineering methods to extract valuable insights from a supermarket’s weekly sales dataset.
Formulated and executed innovative machine learning models (XGBoost, Random Forest, CatBoost) to predict supermarket weekly sales, achieving consistent accuracy levels of 95% and above.
Developed a user-friendly Streamlit program/web page for sales forecasting (Weekly, Monthly, Yearly).

• Utilized Python and Power BI to analyze 20 years’ worth of hospital data, unearthing valuable insights regarding
departmental operations.
• Devised a predictive model to anticipate medical resource consumption, leading to a reduction in expirable medical
inventory within warehouses.
• Constructed a precise predictive model for insurance claims data, accurately forecasting premiums for diverse age
bands of subscribers.
• Implemented a comprehensive fraud detection algorithm by merging Machine Learning (ML) and Deep Learning
(DL) techniques, effectively identifying impending fraud and policy misuse by policyholders.
• Reduced insurance loss-ratio by accurately predicting developing diseases using unsupervised learning.

Utilized Python and Power BI to analyze 20 years’ worth of hospital data, unearthing valuable insights regarding departmental operations.
Devised a predictive model to anticipate medical resource consumption, leading to a reduction in expirable medical inventory within warehouses.
Constructed a precise predictive model for insurance claims data, accurately forecasting premiums for diverse age bands of subscribers.
Implemented a comprehensive fraud detection algorithm by merging machine learning (ML) and deep learning (DL) techniques, effectively identifying impending fraud and policy misuse by policyholders.
Reduced insurance loss-ratio by accurately predicting developing diseases using unsupervised learning.

• Enhanced potential fields path planning for autonomous mobile robot with real-time LIDAR-based obstacle
avoidance.
• Proposed and validated novel algorithms, optimizing autonomy and obstacle avoidance.
• Published paper showcasing expertise in optimizing cost functions and advanced path planning techniques

Enhanced potential fields path planning for autonomous mobile robot with real-time LIDAR-based obstacle avoidance.
Proposed and validated novel algorithms, optimizing autonomy and obstacle avoidance.
Published paper showcasing expertise in optimizing cost functions and advanced path planning techniques.

Acquired comprehensive training in data science encompassing Statistical analysis, Data visualization, Machine Learning (ML), Natural Language Processing (NLP), recommendation systems, and big data technologies.
Employed advanced data analysis and feature engineering methods to extract valuable insights from a supermarket’s weekly sales dataset.
Formulated and executed innovative machine learning models (XGBoost, Random Forest, CatBoost) to predict supermarket weekly sales, achieving consistent accuracy levels of 95% and above.
Developed a user-friendly Streamlit program/web page for sales forecasting (Weekly, Monthly, Yearly)

Utilized Python and Power BI to analyze 20 years’ worth of hospital data, unearthing valuable insights regarding departmental operations.
Devised a predictive model to anticipate medical resource consumption, leading to a reduction in expirable medical inventory within warehouses.
Constructed a precise predictive model for insurance claims data, accurately forecasting premiums for diverse age bands of subscribers.
Implemented a comprehensive fraud detection algorithm by merging Machine Learning (ML) and Deep Learning (DL) techniques, effectively identifying impending fraud and policy misuse by policyholders.
Reduced insurance loss-ratio by accurately predicting developing diseases using unsupervised learning.