Albert Yumol

We will talk about different approaches in teaching Data Science with the Python programming language. As a case study, we will use our own experience in providing Data Science education with Python across different audiences in the Asia Pacific region and share approaches and principles that worked for us. The lecture will serve as an anchor for more conversations and discussions for adapting pedagogy that is most effective for various contexts and settings.

Programming is a fairly new human skill. Unlike natural languages and problem solving that have progressed throughout our evolution, we do not yet have neurological learning pathways dedicated for it. As such, effective pedagogies are still experimental. We will share results of experiments in curriculum and conduct that we did and highlight factors such as project-based learning, purpose-driven education, communal philosophies, applications of Agile principles, relevance to industry, and the unique circumstances of our students.

As technology advances, so as our maps. In this talk, we will explore the ever growing open map data that can help us understand, validate, and explore socio-economic indicators with the aid of network theory and machine learning techniques.

Participants will learn what data are available in OpenStreetMap that can be used to profile cities and municipalities for socio-economic conditions based on proxy variables. These variables include existence of businesses through establishments and buildings, road network densities and complexities, topographical features, vegetation and water indices, etc. Machine learning models will be used for categorization aided by graph metrics. Results will be cross validated with existing city/municipality tags.