Giter Site home page Giter Site logo
Fahmi Zainal photo

fahmizainal17 Goto Github PK

followers: 9.0 following: 37.0 repos: 36.0 gists: 2.0

Name: Fahmi Zainal

Type: User

Company: Pilihan Wibawa/Excelerate Asia/Invoke

Bio: Full-Stack Data Scientist with Physics Background πŸš€| Data Engineer πŸ‘¨β€πŸ’»| Second Lieutenant Reserved Officer πŸŽ–

Location: Kuala Lumpur

Greetings to everyoneπŸ‘‹, I'm Fahmi Zainal

Full-Stack Data Scientist with Physics Background πŸš€| Data Engineer πŸ‘¨β€πŸ’»| Second Lieutenant Reserved Officer πŸŽ–

fahmizainal17

fahmizainal17


🌱 Professional Development

INVOKE SOLUTIONS, Kuala Lumpur (November 2023 – Now)

Data Scientist

Surveys Making, Automation and Optimization:

  • Led the design and implementation of the IVR Data Cleaner, Questionnaire Definer, and Keypress Decoder, significantly improving the efficiency of data processes from 5 hours to 30 minutes.
  • Spearheaded and handled survey projects for call sampling, weighting, and visualization through crosstabs and charts utilizing Google Colab, Azure Databricks, and in-house web applications.
  • Developed and integrated Unified Survey web applications using Streamlit, enhancing collaboration by merging functionalities with team-developed applications in Streamlit and Shiny Apps utilizing FastAPI, supported by Docker, AWS Services, and GitHub Actions (CI/CD).
  • Architected data structure and profiling for utilizing data mining techniques and Geocoding API to map the locality (latitude and longitude) and postcode and other demographics data
  • Taught and guided interns for in-house training in conducting surveys and utilizing Streamlit for proof of concept.

Machine Learning Development:

  • Prepared data, pipelines, designed, and developed predictive models to analyze ROAS Benchmark and Campaign Benchmark, consumer behaviors, and market trends utilizing MongoDB, Databricks, Azure Blob Storage for workflow, and using advanced matching and machine learning techniques, thus enhancing company’s revenue by up to 10% by engaging potential regular clients.
  • Created innovative EDA and model deployment to predict Personal Attributes such as Salary and Income Group, improving demographic targeting accuracy to up to 90% accuracy.

ROAS Dashboard Application:

  • Streamlined and innovated solutions for the ROAS Dashboard application to deliver more precise and filtered results. Enhanced interactivity with users by providing clear graphs for visualization.
  • Worked with Frontend Developer and interacted by creating API Endpoints of the functions to pass the data as of difference in packages usage.

Computer Vision Applications Maintenance:

  • Maintained computer vision projects of FGV oil palm company to optimize the pesticide application.
  • Maintained document parsing automation by implementing TensorFlow and YOLOv5 technologies, facilitating the digitization of invoices and receipts into structured formats for detailed analysis.

Data Warehouse Management:

  • Oversaw the maintenance of the INVOKE’s data warehouse, ensuring robust integration and customization of dashboards to optimize data analytics capabilities.

EXCELERATE ASIA, Kuala Lumpur (September 2023 – October 2023 Excelerate Asia)

Data Analyst (General Assembly)

  • Workforce Dynamics Insights Project: Enhanced data integrity and workforce management through expert data wrangling with Excel and development of Interactive Tableau Dashboards, providing crucial insights into Retention, Compensation Fairness, and Diversity.
  • Global Superstore SQL Project: Leveraged PostgreSQL for robust data management and extraction to Tableau, analyzing trends in product returns to support strategic business decisions thus completing analytics bootcamp training.

πŸ† Achievements

KAGGLE WORLD COMPETITION, Online (April 2022 – June 2023)

Data Scientist

  • Achieved top 28% ranking out of 1908 teams in a Binary Prediction Competition on Smoker Status Using Bio-Signals, leveraging logistic regression, random forest, and tree-boosted algorithms such as Gradient Boosting, LightGBM, XGBoost, and CatBoost.
  • Planned the work meticulously, conducting nightly meetings to discuss strategies, optimize models using Optuna for hyperparameter tuning, and implement a weighted voting classifier for enhanced performance, resulting in an ROC-AUC score of 0.87178 which is 87% accuracy.

πŸ›‘ Leadership

MALAYSIAN ARMED FORCE, Kuala Lumpur (September 2019 – February 2023)

Second Lieutenant Reserved Army

  • Leadership: Commanded a platoon of 89 cadets, achieving high training ratings and improving administrative efficiency, reducing errors by 5%.
  • Communication: Excelled in high-pressure scenarios, coordinating team efforts and earning recognition for leadership during critical simulations.

  • πŸ“ I regularly write articles on www.linkedin.com/in/muhammadfahmibinmohdzainal

  • πŸ’¬ Ask me about Data Science, Data Analysis, Physics, Military, Silat Cekak, Skop Production Movies πŸ˜…

  • πŸ“« How to reach me [email protected]

  • πŸ“„ Know about my experiences www.linkedin.com/in/muhammadfahmibinmohdzainal

  • ⚑ Fun fact I love listening to podcast,reading articles,watching educational to upgrade my skills on Data Analytics,Data Science,Data Engineering and Business because that is what I'm passionate about.Not to mention I love fishing and snorkelling.

  • πŸ” My Expertise

Area Technologies/Tools
IVR and Calls Analytics Google Colab, Streamlit Web Application, Visual Studio Code, Google Sheet API, Google Sheet Dashboard, DataBricks, PySpark
Languages Python, SQL, R, Html5, CSS3 , JavaScript
Cloud & Databases Databricks,AWS API Gateway, AWS Fargate, AWS S3, AWS EC2, AWS ECR, AWS ECS, PostgreSQL
Data Processing PySpark
Dashboarding Excel, Google Sheet, Google Colab, PowerBI, Tableau
Web Development Streamlit Web App, FastAPI
Containerization Docker

Connect with me:

fahmizainal17_ muhammadfahmibinmohdzainal fahmizainal fahmizainal fahmizainal17 @fahmizainal7695

Languages and Tools:

aws azure cplusplus firebase gcp hadoop html5 javascript matlab opencv pandas postgresql python pytorch scikit_learn seaborn selenium tensorflow

Support:

Buy me a coffee
fahmizainal17 fahmizainal17
fahmizainal17

Fahmi Zainal's Projects

30days icon 30days

#30DaysOfStreamlit is a 30-day social challenge for you to build and deploy Streamlit apps.

fastapi_roas_dashboard icon fastapi_roas_dashboard

Separate Backend from Streamlit Frontend, Creates Backend Testing and Endpoint Testing Using Pytest

jom_makan_order_food_website_project icon jom_makan_order_food_website_project

Jom Makan is a food order web application built using ReactJS, CSS, and HTML. It allows users to browse through a menu of available dishes, add items to their cart, and place orders for delivery or pickup.

llama2 icon llama2

This chatbot app is built using the Llama 2 open source LLM from Meta.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    πŸ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. πŸ“ŠπŸ“ˆπŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❀️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.