Rauzan Sumara

I finished my bachelor of science in the department of statistics, Brawijaya University in Indonesia. I obtained my master’s degree at Warsaw University of Life Sciences in Informatics & Econometrics: specialization in big data analytics, Poland. My skills are focused on applied statistical analysis; meanwhile, I am also interested in big data analytics and machine learning. I am used to doing for a living as a freelance data analyst.

Formal Education Link to heading

October 2021 to Present Link to heading

PhD, Technical Informatics and Communications; Warsaw University of Technology, Poland

Funded by:

• Doctoral Scholarship 2021-2025

October 2019 to July 2021 Link to heading

MSc, Big Data Analytics; Warsaw University of Life Sciences, Poland

Funded by:

• West Nusa Tenggara Scholarship 2019-2021

September 2013 to January 2017 Link to heading

BSc, Statistics; Brawijaya University, Indonesia

Funded by:

• Newmont Nusa Tenggara Scholarship 2013-2017
• Data Print Scholarship 2016
• West Sumbawa Government Scholarship 2015-2016

Professional Development Link to heading

• January 2023 - Apache Spark with Python - Big Data with PySpark and Spark by Level-Up.One (Online Course)

• December 2022 - Introduction to Data Studio by Google Analytics Academy (Online Course)

• December 2020 - Learn Database Design with MySQL by Eduonix (Online Course)

• August to September 2019 - Programming Essentials in Python (Online Course)

Funded by:

• The Ministry of Communication and Information Technology, Indonesia.

• October to December 2018 - Big Data & Artificial Intelligence Training (Offline Course)

Funded by:

• The Ministry of Communication and Information Technology collaborated with Department of Electrical Engineering, Sepuluh Nopember Institute of Technology, Indonesia.

Work Experiences Link to heading

Data Analyst | February 2018 to Present Link to heading

at RS Data Statistics – Taliwang, West Nusa Tenggara;

Provide high quality services in data analytics, research, survey sampling methodology, and implementing developed technology for researchers, lecturers, and companies in Indonesia. For more detail about my business RS Data Statistics, kindly go to RS Data Statistics. I look for projects at projects.co.id and fiverr.com as well.

Instructor - Data Business Analytics & Operations | February to July 2022 Link to heading

at Ruang Guru Indonesia – Jakarta, Indonesia;

(1) teach a data-driven approach to the world of business. It is about utilizing a practical statistics and data mining and modeling in order to deliver a new insight for the business, (2) teach the most important processes in business analytics, such as descriptive, diagnostic, predictive and prescriptive analytics, (3) prepare class sessions and assignments to help students grasp course content and how it integrates with overall student learning outcomes for the course, (4) teach courses in accordance with defined course standard outcomes. Used software: Python, PostgreSQL, Tableau.

Mentor - Accelerated Machine Learning | February to July 2022 Link to heading

at Zenius Indonesia – Jakarta, Indonesia;

(1) teach theory and hands-on ways to learn machine learning for college students, (2) teach to solve real-world problems using modern tools and machine learning algorithms, (3) report all necessary information related to students, (4) monitor and assess students’ progress on a regular basis, etc. Used software: Python.

Data Analyst & Consultant | August 2017 to January 2018 Link to heading

at Arena Statistics – Malang, East Java;

(1) Interpret, analyze data using statistical techniques and provide reports to the clients, (2) Provide statistical solutions to problems of clients which can be accounted for, (3) Give statistical learning workshop, and (4) Create and improve workshop handbooks.

Technical Experience Link to heading

• October 2023 to February 2024, Teaching Computer Statistics Lab, Faculty of Mathematics & Information Science, Warsaw University of Technology.
• October 2022 to February 2024, Teaching Introduction to Machine Learning Lab, Faculty of Mathematics & Information Science, Warsaw University of Technology.
• October 2021 to February 2022, Teaching Introduction to Machine Learning Lab, Faculty of Mathematics & Information Science, Warsaw University of Technology.
• January 2017, Assistant lecturer at Training Data Analysis Using Software Statistics for Officers Learning Indonesian Agency for Agricultural Research and Development (IAARD), Grage Hotel, Malang City.
• September 2016 to January 2017, Lab Assistant of Computational Statistics, Department of Statistics, Brawijaya University.
• August to September 2016, Practical Work at Bank Central Indonesia, Malang City.
• September 2015, Study at Bank Central Indonesia, Nielsen, and MarkPlus, Jakarta City.
• August to December 2015, Lab Assistant of Basic Computation, Department of Statistics, Brawijaya University.
• April 2015, Study at PT. Yakult Indonesia Persada and PT. Indofood Sukses Makmur.
• February to June 2015, Assistant of Introduction to Probability, Department of Statistics, Brawijaya University.
• January 2015, As A Reporter for Gunturmuli Megazine of West Sumbawa Students.

Research Link to heading

2024

The Use of Virtual Reality Platforms to Improve Students’ Speaking Skills (A. Rahman, Umar Umar, Zainudin Hassan, and Rauzan Sumara) Read More…

2023

Siamese Network with Gabor Filter for Recognizing Handwritten Digits (Rauzan Sumara) Read More…

2021

Random Subspace Ensemble Learning for Cancer Detection Based on Microarray Data (Rauzan Sumara) Read More…

2019

Posterior Predictive of Bayesian Vector Autoregressive (BVAR) and Adjusting Transformation on the Spatio Temporal Disaggregation Method: Predict Hourly rainfall data at the out sampled Locations (Suci Astutik, Umu Sa’adah, S. Adhisuwignjo, and Rauzan Sumara) Read More…

2018

The Daily and Hourly Rainfall Data Modeling Using Vector Autoregressive (VAR) with Maximum Likelihood Estimator (MLE) and Bayesian Method (Case Study in Sampean Watershed of Bondowoso, Indonesia) (Suci Astutik, Umu Sa’adah, S. Adhisuwignjo, and Rauzan Sumara) Read More…

Algoritm of Bayesian VAR on Spatio Temporal Disaggregation Method (Suci Astutik, Umu Sa’adah, S. Adhisuwignjo, and Rauzan Sumara) Read More…

2017

Approaching Predictive Bayesian Posterior Distribution to Rainfall Model (Suci Astutik, Umu Sa’adah, S. Adhisuwignjo, and Rauzan Sumara) Read More…

Bayesian Vector Autoregressive Model (Case Study in Analysis of Relationship Between Economic Growth and Export in Indonesia) (Rauzan Sumara) Read More…

2016

Estimating of ARIMA with Outlier Model for Forecasting Inflation in Malang City (Rauzan Sumara) Read More…

Modelling of Relationship Between Gross Domestic Product and Foreign Direct Investment in Influencing Indonesia Economic Growth (Rauzan Sumara, Novilia Fitra Sari N., Sonny Bangkit W., and Atika Qurotu A.) Read More…

2014

FERADISA (Fermentation of Extract from Soursop Leaf and Clover as Biopestisida) to Control Pests of Apples in Sumbergondo District, Batu City (Dwi Lina N., Dewi Ratih Tirto S., Tamilia Septia S., and Rauzan Sumara) Read More…

Academic Project Undertaken Link to heading

Project 11 : ARIMA with Intervention Model for Predicting Consumer Price Index (CPI) in Malang City, Indonesia; February 2021

This was the final project from the Theory of Forecasting and Simulation course. The project aimed to model the Consumer Price Index (CPI) in Malang City. We observed series from January 2006 to June 2017. Because there are interventions that occurred in June 2008 (Intervention I) and January 2014 (Intervention II), the change of the reference basis for calculating the CPI, Autoregressive Integrated Moving Average (ARIMA) model with Intervention will be used, then the best model was performed for predicting the CPI for the next 12 months Read More…

Project 10 : Implementation of GAN and cGAN Models; January 2021

As the final project of Deep Learning in Python Course, I was trying to detail what Generative Adversarial Network (GAN) and Conditional Generative Adversarial Network (cGAN) are. I also explain and give an implementation of both of them separately. Code also can be obtained from my Github. Those models are the most exciting ideas in computer science today. Two models are trained simultaneously by an adversarial process. A generator (the artist) learns to create images that look real, while a discriminator (the art critic) learns to tell real images apart from fakes Read More….

Project 9 : Predict Churning Customers; January 2021

This was my final project of Data Mining Course; the dataset and Python code can be downloaded on my Github. A manager at the bank is disturbed with more and more customers leaving their credit card services. They would really appreciate it if one could predict who is going to get churned so they can proactively go to the customer to provide them better services and turn customers’ decisions in the opposite direction. This dataset is original from Kaggle. The dataset consists of 10,000 customers mentioning their age, salary, marital status, credit card limit, credit card category, etc. There are nearly 18 features. From this data set, we can predict the customers who are going to stop using credit cards and can make an offer to customers to retain them Read More….

Project 8 : Social Network Analysis Using Gephi; June 2020

In this project, I tried to track tweets related to covid-19, what accounts were mostly and actively talking about the coronavirus, and how to structure relationships that connect individuals or behaviors of social relations. The dataset for this social network analysis was taken from Twitter using the crawling feature in R Studio. I used Twitter data mainly related to @WHO and #COVID19 tweets in the USA Read More….

Project 7 : Build CNN Model to Classify Images of Drill Holes; April 2020

This project presents a deep learning approach to drilling condition assessment. The assessment regarding the level of the drill wear was done on the basis of the drilled hole images. To prepare images for recognizing the drill condition, the elimination of the artifacts (unnecessary part of images around hole) was done first. Moreover, every image was cropped to 170x170 pixels, and conversion from RGB to grayscale has been applied. Such prepared images were used directly as the input data in deep learning. We have applied size of the receptive field to equals 5x5 pixels and 32 filters in the layer, set the stride size equal to one in the convolutional layer and the value of two in the pooling layer. It consists of successive three convolution ReLu (Rectified Linear Unit) layers, followed by the pooling layers for feature learning and the fully connected softmax used as a classifier Read More….

Project 6 : QR Code Generator and Scanner Mobile Apps; October to January 2020

This is an android apps that is not only to describe and maintain the information about equipment. It also helps the user manage all the equipment already provided in school by specific features of the given software. The purpose of the application is to help the staff to define the equipment just by scan it on the smartphone. The application was designed to make good management in the inventory at a school. This application can be installed on a mobile phone, specifically in an android application Read More….

Project 5 : Non-Clickbait Detector Apps; October to December 2018

This was the final project of big data & artificial intelligence training scholarship provided by Ministry of Communication and Informatics of Republic of Indonesia (KOMINFO). The purpose was to create android apps in order to detect non-clickbait news on the internet. For classifying, my team and I developed a semi-supervised learning algorithm in Python. The application can be downloaded in the google store named “kliken - Aplikasi Berita” Read More….

Project 4 : Takagi-Sugeno Fuzzy Modeling; April to June 2016

This project was a part of the final exam of Fuzzy Logic Course. The aim was to create functions (coding) on R based on stages and theory of Takagi-Sugeno fuzzy modeling. This technique can be used to predict time series data Read More….

Project 3 : GUI for Statistical Distribution; April to June 2016

In completing the final exam of Advanced Computational Statistics Course, I created a Graphical User Interface (GUI), The simple statistical distributions in R. Two distributions were made, 1). Discrete distributions consist of binomial, Poisson, geometric, and negative binomial distribution. 2). Continuous distributions consist of normal Z, Student t, Chi-Square, and Fisher distribution. Through the GUI, we can easily show probability, quantile, plotting, and generating data Read More….

Project 2 : Threshold Autoregressive (TAR) and Smooth Transition Autoregressive (STAR) Model in Empirical Finance; May 2016

We aim to study non-linearities in the quarterly Indonesia Interest Rates (1958-1970) by means of threshold autoregressive and smooth transition autoregressive models. There are two beneficial forms of the STAR model: the Logistic STAR and the Exponential STAR. We compared these models, AR, TAR, Logistic STAR, and Exponential STAR, based on AIC criteria. The result showed there was some non-linear structure to be modeled, and STAR adequately describes in-sample movements of interest rates. The Logistic STAR was performing better than other models. The model allows the autoregressive parameters to change slowly, and in general, the STAR family of models is a suitable tool in explaining some extreme events Read More….

Project 1 : The Application of Error Correction Model (ECM) in Handling Spurious Regression; April 2016

Time series data consist of dividends and profits quarterly from 1970 to 1991 was given. There is a positive correlation between those two variables. After performing the regression model, which is dividends as dependent and profits as the independent variable, It was proven that spurious regression was present so that we identified cointegration by using the Engle-Granger test. In handling long-run stochastic trends (cointegration), ECM was applied. ECM is a theoretically-driven approach useful for estimating both short-term and long-term effects of one-time series on another Read More….