I’m a dedicated data scientist with a goal-oriented mindset and a "Can Do" attitude. I thrive on transforming raw datasets into meaningful insights and actionable solutions.
My experience spans building automated data validation systems in the UK, reducing manual data wrangling by 70–80%, and creating intelligent workflows that help teams make data-driven decisions efficiently.
I work at the intersection of logic, creativity, and curiosity — leveraging Python, SQL, machine learning, Tableau, and smart automation to solve real-world problems. From building scalable ETL pipelines and predictive models to visualizing insights that drive impact, my goal is simple: make data work smarter, not harder.
If your project needs clarity, intelligence, and a touch of creativity — that’s where I come in.
I am also open to freelance, remote, or pro-bono opportunities, collaborating with teams or individuals in the data science community to create meaningful impact.
The challenge revolved around establishing a process for self-sustained data validation and scoring, all while mitigating the dependency on metadata information. The core issue lies in the laborious data-wrangling efforts undertaken by data scientists or analysts, consuming a substantial 70 to 80% of their time and resources when preparing data sets for machine learning. Additionally, clients encountered difficulties locating suitable data sets aligned with their specific needs, often requiring meticulous considerations such as target audience, geographical coverage, timeliness, and historical relevance.
The Flask web-based app, communicating seamlessly with Python code, empowers data providers and clients to autonomously validate data set health, resulting in a remarkable 70-80% reduction in manual effort and development costs. By harnessing Alqami's algorithm, it dynamically scores supervised/unsupervised data, rapidly producing results without reliance on metadata. Encompassing Data Ingestion, Wrangling/Cleaning, EDA, and automated report generation, the Python-powered scoring effortlessly generates accessible scores through the web.
• Performed data extraction from Amazon S3 Bucket, subsequently storing the transformed data into user-defined directories for seamless future analysis.
• Executed generic ETL pipeline tasks, Data Wrangling/Cleaning, Exploratory Data Analysis (EDA), and automated report generation, leading to 70-80% reduction in data scientist time and cost for further machine learning operations.
• Crafted Contextual Analysis, Correlational Analysis, Descriptive Analysis, and visualization components aligning with company scoring criteria, increasing clients' chances of purchasing datasets by 80% compared to viewing samples.
• Iteratively refined the solution for effective adaptability, handling diverse datasets and exceptions without crashes, resulting in 100% optimized and faster reporting than human analysts.
Harpreet Geekee, CTO at Alqami:
"A strong data scientist with a outstanding analytical and programming skillset.Rana has ability to think out of the box, very handy in wrangling (EDA) the datasets and various supervised and unsupervised machine learning algorithms."
Jon Peters, CFO at Alqami:
"After completing his Masters degree, Rana joined Alqami as an intern and quickly fit into the our startup culture; a hard working, collaborative team player and problem solver. He transitioned to F/T employee, data scientist and formidable first line coder (python)."
Lucy Lynch , Industry Project Director | University of Salford:
"I had the pleasure to mentor Rana through the Nurture Programme. Rana was diligent and curious and demonstrated a great deal of resilience. Rana was a pleasure to work with and I sincerely wish him every success fir the future.
Kaveh kiani , PhD | Lecturer in Data Science | University of Salford:
"As a Lecturer at the University of Salford, I taught him the principles of data science module, and I noticed he is a quick learner who focuses on understanding the main concepts. With his positive approach, he has got hands-on experience in descriptive statistical analysis and data visualisation after completing the module. Rana is a pleasant person to work with."
Apart from exploring data science, I am passionate about contributing to projects that create meaningful impact. I am open to freelance, remote, or pro-bono opportunities to collaborate with teams and individuals in the data science community.
Outside of work, I enjoy learning new tools and techniques, keeping up with AI/ML advancements, and applying data-driven insights to solve real-world problems.