Abstract: Economists around the world often rely on limited survey data to conduct research in their respective fields. The surveys, whether produced locally or by an international entity, are not only quite expensive but also limited. (1) Timeframe and frequency. Surveys might (if we are lucky) be conducted every year. But often times the gap is more likely closer to every 5 years. (2) Geographically too. Data pertaining to remote or “sensitive” regions might never get recorded. (3) Accuracy and trustworthiness. Some data can be (explicitly or accidently) unreliable and erroneous. The aim from this talk is to not only highlight some of the benefits of Alternative Data but also break down some of the technical barriers to entry. I will specifically walk through a use case that utilizes NOAA*’s (open source!) Nightlight Satellite Imagery. (All possible from within a personal machine.)
I’ve been fascinated by the power of alternative data (more specifically satellite imagery). While there are various point of views regarding the usages of this technology, the use case I would like to present highlights the significant benefits of such a resource: democratizing access to data and helping researchers have more up-to-date, trustworthy and affordable data especially in countries that need it the most.The project that I would be demoing utilizes QGis (open source software) to process the raw images and apply geographical (eg. country) borders. It then uses R/Python to analyze and visualize the numeric output data.
*National Oceanic and Atmospheric Administration (NOAA)
Bio: Before transitioning to data science, Mariem was a software engineer. In her current role, Mariem works on various data sets and her projects touch upon BI, automation, prediction and NLP. In addition to her day-to-day role, Mariem has a strong interest in tech for social good. She enjoys researching ways to use data science for economic growth in developing countries, joining hackathons for non-profits and advocating to get a broader set of people into technology. Mariem has previously created and taught machine learning, Python and web programming workshops. She has also been featured in the book, "Her STEM Career: Adventures of 51 Remarkable Women" aimed at introducing girls to various STEM fields, and featured in the documentary “Data Science Pioneers - Conquering the Next Frontier”. Mariem holds a Bachelor’s in Computer Science from Smith College (MA) and a Master’s in Data Science from Columbia University (NY).
Data Scientist | Credit Susse