👋 Hi, I am Golfianto, a mechanical engineer with a passion for enhancing urban transportation systems through data-driven solutions. With four years of experience at PT. MRT Jakarta, I've led engineering efforts in ensuring project compliance and efficiency. Armed with a master's degree from Karlsruhe Institute of Technology, I possess strong analytical skills and proficiency in CAE/CAD and programming.
In my recent journey into data science, I've delved deep into Python, HTML5, SQL, and Machine/Deep learning, honing my expertise through hands-on projects and collaborative efforts. I'm driven by a desire to apply my diverse skill set to contribute meaningfully to the development and sustainability of urban infrastructure in Indonesia and beyond.
- 👀 I’m looking to collaborate on any data science project
- 📫 How to reach me: https://www.linkedin.com/in/hari-golfianto/
- 📂 Here are some projects that I have done and been involved in.
| No. | Project name | Description | Tools/libraries/methods |
|---|---|---|---|
| 01 | Time series predictions | A transportation company has collected historical data on taxi orders at the airport. To attract more drivers during peak hours, it is necessary to predict the number of taxi orders for the next hour. A model for such prediction will be created. | pandas, numpy, simple exponential smoothing, Holt, ARIMA, random forest regression |
| 02 | Credit card scoring | Preparing reports for the credit division of a bank. Determining the effect of a customer's marital status and the number of children sought on the probability of default in loan repayment. | pandas, matplotlib.pyplot |
| 03 | Predicting telco client churn | A telecommunications operator offers landline communication and internet services to its clients. They are interested in forecasting churn among their clients. The goal is to identify potential churners and take proactive measures to retain them by analyzing their personal data, contract details, and service usage patterns. | seaborn, plotly, sklearn (logistic regression, decision tree, random forest), smote, xgboost |
| .. | Upcoming project will be added here |
- Hi, I plan to embark on a 30-Weeks of Code Challenge as a series of side projects related to railway engineering and rolling stock systems. The objectives include continuous learning, skill improvement, technology exploration, problem-solving training, and expanding my professional network. Currently I am collecting project ideas, and I am preparing a tangible schedule. Instead of the common 30-day code challenge, I plan to undertake a 30-weeks due to my routines.
- Rules:
- Projects should be small to medium scale in scope.
- Allocate a minimum of 4 hours per week to coding or project work.
- Adjust project methods and outcomes to accommodate constraints such as available time and knowledge.
- Commit to completing 6 to 8 projects in total.
- Project topics must be related to railway/rolling stock areas and may involve data analysis, machine learning, automation, and CAE/CAD analysis tasks.
- Primary tools utilized will be Python and CAE/CAD software.
- Updates will be shared through GitHub
- Please reach out to me with any great project ideas related to railway engineering and rolling stock systems. Selected (3 to 4) ideas will be adjusted to fit my limitations.
- I believe this initiative has the potential to not only enhance my skills and knowledge but also contribute positively to advancements within the railway industry.
- Additionally, I am open to collaboration opportunities.
| No. | Project name | Description | Tools/libraries | Deadline | Status |
|---|---|---|---|---|---|
| 01 | Single train simulation | This project is a simulation of a single train moving along a predefined track. The simulation is designed to demonstrate the basic principles of train dynamics and control systems, providing a visual and interactive way to explore how a train operates under various conditions. | python, numpy | W1 July 2024 | DONE in W2 June, will be improved |
| 02 | Report automation in railway | This project automates the generation of reports for train procurement forecasts using data analysis and forecasting techniques. It streamlines the procurement planning process, ensuring timely and efficient procurement of trains. The system handles various procurement data, generates insightful forecasts, and produces comprehensive reports to support decision-making | python | W4 July 2024 | - |
| 03 | Computer vision: Object detection in railway | .. | W4 Aug 2024 | - | |
| 04 | Wheel rail contact | .. | FEA | W4 Sep 2024 | - |
| 05 | Impact simulation | .. | W4 Oct 2024 | - | |
| 06 | .. | W4 Nov 2024 | - | ||
| 07 | .. | W4 Dec 2024 | - | ||
| .. | .. | .. | .. | - |
Thank you for visiting