Email: gerrydito@apps.ipb.ac.id | Website: gerrydito.github.io/about |
Gerry Alfa Dito Lecturer in Statistics and Data Science
EDUCATION
Magister – Statistika | |
IPB University | Sep 2017 — Jan 2020 |
Thesis: "Study of Super Learner Development with Cuckoo Search for Increasing Classification Performance" | |
Supervisor: Dr. Bagus Sartono, Dr. Eng. Annisa, Dr. Anang Kurnia | |
Sarjana – Matematika | |
Lampung University | Sep 2012 — Apr 2016 |
Specialization in Statistics | |
Bachelor’s thesis: "Neural Network Fuzzy Learning Vector Quantization (FLVQ) to Identify Probability Distributions" | |
Supervisor: Dr. Warsono and Dr. Dian Kurniasari | |
Certified Data Analyst | |
Global ICT Professional Certification Institution | Jul 2024 — Jul 2027 |
View Certification |
WORK EXPERIENCE
Lecturer in Statistics and Data Science | |
School of Data Science, Mathematics and Informatics | Apr 2020 – Present |
IPB University | |
Contributing Write | |
Info Komputer | Oct 2019 – Mar 2020 |
Research Assistant | |
Department of Statistics | Oct 2019 – Mar 2020 |
IPB University | |
Statistical Consultant | |
Dokter Data | Dec 2017 – Oct 2019 |
Lembaga Ilmu Pengetahuan Indonesia(LIPI) | Sep 2018 – Oct 2018 |
Detective Data | Sep 2016 – Aug 2017 |
Teaching Assistant | |
Department of Mathematics | Sep 2013 – Jan 2016 |
Lampung University | |
Data Analyst | |
Representative Office of Bank Indonesia Lampung | Jan 2015 – Feb 2015 |
RESEARCH INTEREST
My research interests lie at the intersection of statistical theory, machine learning, and applied data science, focusing on both theoretical advancements and practical applications. Specifically, my work addresses the following areas:
Bayesian Methods: Development of scalable Bayesian inference techniques, with a focus on Markov Chain Monte Carlo (MCMC) methods and Variational Inference.
Interpretable Machine Learning: Developing machine learning models that are inherently understandable by humans. This involves designing algorithms where the decision-making process is transparent and directly comprehensible, such as sparse linear models, decision trees with a limited number of nodes, and rule-based models. My research in this area emphasizes the creation of models that maintain high performance while ensuring that the underlying mechanisms and predictions are intuitive and easily interpretable. This is particularly important in high-stakes applications such as healthcare and finance, where trust and accountability are crucial.
Explainable Machine Learning: Developing methods to enhance model transparency and interpretability in complex machine learning models, particularly deep learning and ensemble methods. This includes both post-hoc interpretability techniques and the development of inherently interpretable models.
Applications in Biostatistics, Economics, and Social Sciences: Applying advanced statistical and machine learning techniques to real-world problems in health, economics, and social science.
SELECTED PUBLICATIONS
SOFTWARE AND TECHNICAL SKILLS
Programming Languages:
R: Extensive experience in data analysis, statistical modeling, and visualization using R. Proficient with libraries such as
tidyverse
ecosystems.Python: Skilled in Python for data science and machine learning, using libraries such as
pandas
,NumPy
,SciPy
, and machine learning tools likeScikit-Learn
,XGBoost
, andmatplotlib
.
Statistical Software:
SAS: Proficient in data manipulation, statistical analysis, and predictive modeling using SAS. Experienced with SAS procedures for regression, time series analysis, and generalized linear models.
Machine Learning Frameworks:
Scikit-Learn: Expertise in implementing machine learning algorithms, including classification, regression, clustering, and model evaluation techniques.
Tidymodels: Skilled in using the Tidymodels framework for modeling in R, including feature engineering, cross-validation, and building machine learning pipelines.
Deep Learning Frameworks:
TensorFlow: Experienced in building, training, and deploying deep learning models for tasks such as image recognition, natural language processing, and time-series forecasting.
PyTorch: Proficient in developing and fine-tuning deep learning models using PyTorch, with applications in neural networks, convolutional networks, and reinforcement learning.
Bayesian Modeling:
Stan: Proficient in Bayesian inference and probabilistic programming using Stan, with experience in hierarchical modeling, MCMC methods, and advanced sampling techniques.
CONSULTING AND INDUSTRY COLLABORATION
Workshop Instructor – Pendidikan In House Training (IHT) Kaidah Penyusunan Riset, BRI Corporate University, PT. Bank Rakyat Indonesia (Persero) Tbk – 23 Aug 2024Developed custom training materials focused on data exploration, statistical modeling, and interpretation of results for business banking applications using Jamovi.
Delivered hands-on workshops on data exploration, statistical modeling, and interpretation of results for business banking applications using Jamovi.
Developed forecasting models for FFB (Fresh Fruit Bunch) Production in Oil Palm Plantations using XGBoost algorithms.
Utilized R to create data pipelines, perform feature engineering, and deploy XGBoost models algorithms to forecast FFB (Fresh Fruit Bunch) Production in Oil Palm Plantations.
Developed custom training materials focused on spatial data exploration and spatial regression modeling using R.
Delivered hands-on workshops on spatial data exploration and spatial regression modeling using R.
Developed models for identification Identifying factors that affect household poverty status.
Developed models for effective policy interventions for extreme poverty alleviation
Developed a machine learning model for monitoring crisis management protocol indicators in the stock market.
Utilized R to create machine learning pipelines to monitor crisis management protocol indicators in the stock market.
PROFESSIONAL DEVELOPMENT
Certification
How to Write a Successful Research Paper Udemy (2024) Completed courses on UNDERSTAND the logic and structure of a research paper, IDENTIFY the qualities that make a research paper effective.
The Data Science Course: Complete Data Science Bootcamp Udemy (2022) Completed courses on data science field and the type of analysis carried out, Mathematics , Statistics, Python, Data Visualization, Machine Learning, Deep Learning View Certification
Deep Learning A-Z: Hands-On Artificial Neural Networks Udemy (2021) Completed courses on neural networks, CNNs, RNNs, Self-Organizing Maps, Autoencoder, and practical deep learning projects using TensorFlow and PyTorch. View Certification