Raden Muhammad Hadi Suryo Suharto

Principal Data Scientist

Data scientist based in Jakarta with 8+ years of experience across various industries. Focused on data product development using Python & R. Specializing in aquaculture technology solutions and driving sustainability through data-driven initiatives.

Email LinkedIn GitHub

Experience

Principal Data Scientist

DELOS

Jakarta | 2024 - Present

  • Leading data-driven initiatives to optimize shrimp management systems and drive sustainability.
  • Specializing in aquaculture technology solutions.

Data Science Team Lead

DELOS

Jakarta | 2022 - 2024

  • Built data strategy for science teams.
  • Developed mathematical and statistical models for shrimp growth prediction and farm operation optimization.
  • Led BI and Deep Tech Division team to improve core business via digital transformation.

Senior Data Scientist

DELOS

Jakarta | 2022 - 2022

  • Built data strategy for science teams.
  • Developed mathematical and statistical models for shrimp growth prediction and farm operation optimization.

Data Scientist - Financial Services

Bukalapak

Jakarta | 2021 - 2022

  • Analyzed financial services and virtual products performance.
  • Projects: Mutual Funds Recommendation, Fire Insurance Analysis.

Data Scientist - Growth

Bukalapak

Jakarta | 2020 - 2021

  • Analyzed and modeled customer behavior using analytics, interpretable ML, and causal models.
  • Projects: In-Marketplace game analytics, Voucher distribution, Game player segmentation, Voucher dependence scoring.

Research Development Team Lead

Quantus Telematika Indonesia

Bandung | 2020 - 2020

  • Led R&D team to create data products and explore new DS/ML methodologies.
  • Project: OCULUS-DEI (Social Media Analyzer).

Mathematics Modeler - R&D Department

Quantus Telematika Indonesia

Bandung | 2018 - 2020

  • Built solutions/models for data science and mathematical modeling problems.
  • Developed web applications (Python, R, Java backend) and performed data analysis (text mining, NLP).

Data Science Consultant

StatsMaster (Self-employed)

Jakarta | 2013 - Present

  • Provided data science consulting, data product development, training, and talent consulting.

Data Science Mentor

Freelance

Anywhere | 2019 - Present

  • Taught data science courses for various organizations (DQLab, Arkademy, Dibimbing.id, etc.).
  • Topics: R/Python/KNIME, Analytics Lifecycle, ML, Deep Learning, NLP, Data Product Dev.

Education

Bachelor's Degree in Mathematics

Indonesia University of Education

Bandung, Indonesia | 2011 - 2015

Graduated with Honors. Major: Pure Mathematics (Specialization: Algebra - Operator Theory and C*-Algebras).

Final Thesis

Skills

Programming & Databases:

R Python SQL Javascript PostgreSQL MySQL SQLite DuckDB Cassandra Redshift BigQuery

ML & LLM Frameworks:

Scikit-Learn Tidymodels SkTime SkForecast OpenAI Groq Gemini Ollama LangChain Huggingface

Data Product Dev & Deployment:

Streamlit Shiny Dash Mesop Gradio Docker

Data Science Skills:

Explanatory Model Analysis, Time Series Analysis & Forecasting, Model Audit, MLOps, A/B Testing, Multi-Criterion Decision Analysis, Machine Learning Modeling, Mathematical Modeling, Causal Analysis

Domain Expertise:

E-commerce, Aquaculture, Financial & Digital Services, Consulting

Portfolio

Total Hemocyte Counter

Detect and count shrimp hemocytes from images for health inference. [Company Project]

Tech: Python, Streamlit, YOLOV5

HR Attrition Dashboard

Monitor employee performance and predict attrition with ML explainability.

Tech: Python, Gradio, Scikit-Learn, LIME

View Project

MNIST Canvas

Simple app demonstrating deep learning image classification.

Tech: Python, NumPy, Gradio, Tensorflow, PIL

View Project

Twitter Analysis - Presidential Election 2019

Analysis of trends, sentiment, and networks from Twitter data using R.

Tech: R, RStudio, Rmarkdown, rtweet, tidyverse, graphTweets, sigmajs

View Analysis

Text Mining & Wordcloud Analysis (Beritagar)

Tutorial on web scraping and text analysis using R.

Tech: R, Tidyverse, rvest, tidytext, corpus, wordcloud2

View Tutorial

Featured Articles & Talks

AITALK: Agentic Large Language Model

Workshop exploring LLMs as intelligent agents, using tools like LangChain and AutoGen.

Watch Talk

Customer Data Analysis Best Practices

Presentation covering cohort analysis, correlation, segmentation, marketing attribution, and EMA.

Watch Talk

Process Mining: Uncover Insights from Flow-based Events - Part 1

Medium article on using process mining to analyze user behavior in a game.

Read Article