About
About Me
I am currently in career development in the area of Data Science and Artificial Intelligence. This is my Portfolio to keep track of my projects, contributions & publications.
My background in Computer Science – I am passionate about data analytics, numbers, and programming, but also have software engineering & development experiences.
I am actively looking for job opportunities where I can help companies in optimizing their businesses and product development by providing meaningful data insights through Python, SQL, and Tableau (or similar technologies).
Feel free to contact me if you found my website useful and think I might be a good fit or simply would like to connect ☕
My Background
My name is Sulaiha Subi, you may call me "Sue" for short. I am Data Scientist at a startup company in Kuala Lumpur with industry experience in Data Science, Deep Learning and Machine Learning. I joined the company as the first Data Scientist working on every aspect of Data Analytics and Predictive Modelling. I am the main contributor to the development of Data Science in the company. My other big responsibilities as Data Scientist are to develop new client relationships or potential collaboration, meet & present the company's product/services & highly responsible to prepare high business value commercial proposals across different domains of the industries (client-facing skills).
I also currently collaborating with 47 other AI Engineer from 18 countries for 8 weeks challenge as a Machine Learning Engineer (part-timer) at Omdena. In this project I apply my knowledge and skills to build an automated plant health prediction model, using drone-derived multispectral and thermal data combined with weather and irrigation data.
I am proficient in Python (Pandas, NumPy, OpenCV) programming language and data visualisation with Tableau and Dataiku. I am enjoyed working with large datasets including cleaning, preprocessing, connecting and mining those data. I have alredy worked with few high value use case in Insurance, Marketing and Edge Computing like Drone where I built Random Forest, XGBoost, SVM, Regression and Image Classifiaction. Some of these model developed end-to-end in Dataiku DSS Platform.
Projects I worked on include Text Pre-processing for NLP in the documents management system, Integrated Data Intelligence (IDI), and applied cutting-edge Computer Vision skills for POC in face recognition & counting for productivity measurements. More details about this project can be found here:
My Journey to Data Science
As an undergraduate in Information System, a unique program that focus on both technical and managerial aspects. During my studies as undergraduate, there are few subjects in IS like Intelligence System, Data Mining, Data Visualisation and Collective Intelligence (NLP like Text & Speech Processing) that encourage me to pursue more in Data Science.
After graduation in 2019, in 2020 I continue to pursue my Data Science journey by taking Deep Learning Certification (Junior Deep Learning Engineer) and one month training which covered in-depth study of data pipelines and deep learning model development from deploying deep learning to production.
Along the way of my journey become Data Scientist (current role), I developed my skills in Data Science for Marketing as Digital Marketer (Analysing Marketing Data), I became part time apprentice which is deep learning infrastructure development and then I joined IoT Company at Cyberjaya as Software Engineer where I worked with IoT engineer, to perform and design testing protocols/prototypes to ensure that the product is fully tested before the deployment. Not limited to that, I actively encouraging myself to collaborate in solving real-world project as Machine Learning Engineer.
I dreamed about predicting the future using past data & wanted to be a part in Data Analytics Team - before all the hype around data science. Therefore in 2020, I decided to fulfill my dream to move from Labuan to Kuala Lumpur and become a Data Scientist.
My Data Science Skills
I have for one and half years experinced in Data Science. I already built few end-to-end Machine Learning Models & Predictive Analytics Projects based on real-world problems.
Having a background in Computer Science allows me to learn faster and quickly adapt into the trends of technology. The experience that I acquired through out this years are:-
- Cleaning and transforming data with Python libraries (Pandas, Numpy)
- Data Preprocessing (One-Hot Encoding, Feature Scaling, Data Normalization, Dealing with Missing Values, Dimensionality Reduction with PCA)
- Data Visualizations and Exploratory Data Analysis (EDA) with Dataiku
- Advanced Deep Learning for Computer Vision & Natural Language Processing (NLP)
- Training Machine Learning models using best practices (including train/val/test splits, class balance, outlier detection/removal)
- Knowledgeable in how to image processing, image classification, object detection to image segmentation, using the Deeplearning4j framework
- Knowledge in machine/deep learning, optimization, probability theory, and statistical inference
- Hyperparameters tuning
- End-to-end Machine Learning pipelines
- Knowledge in Cloud Computing like AWS EC2
- Database Management like PHP & SQL
Competition
I love challenges and collaboration within the Data Science Community and Data Ethusiast.
Last July 2021, I was actively participated in Dataiku Frontrunner Awards as the only submission presenting the use case from APAC region. I am proudly said that my use case was being published by Dataiku Community
More details about the use case, can be read here: Dataiku Frontrunner Awards!
Hobbies: Taekwondo & Yoga
One of the biggest achievment in my life is getting black belt 1st Dan in Taekwondo (Taekwondo Malaysia). Not limited to Taekwondo, I love doing Yoga during my leasure time to increase my flexibility and endurance!
“The quote that always push me to the new level in life is everything we do is a process, keep going even the process taking longer because rome was not built in a day”