Ana Bossler's Projects
Agent-based computational Economics, the Python library that makes AB modelling easier
The analysis and prediction of macroeconomic time-series is a factor of great interest to national policymakers. However, economic analysis and forecasting are not simple tasks due to the lack of a precise model for the economy and the influence of external factors, such as weather changes or political decisions. Our research is focused on Spanish speaking countries. In this thesis, we study different types of neural networks and their applicability for various analysis tasks, including GDP prediction as well as assessing major trends in the development of the countries. The studied models include multilayered neural networks, recursive neural networks, and Kohonen maps. Historical macroeconomic data across 17 Spanish speaking countries, together with France and Germany, over the time period of 1980-2015 is analyzed. This work then compares the performances of various algorithms for training neural networks, and demonstrates the revealed changes in the state of the countries’ economies. Further, we provide possible reasons that explain the found trends in the data.
Reinforcement learning classes/Mathematics Institute Program(UBA)
model meant to predict the risk of elevated childhood blood lead levels at a geographically aggregated scale
alguna clase de la escuela de verano de ciencia de datos
ejercicios python y r
material utilizado en clase de nuevas tecnologías
material desarrollado en clase de economía de la vivienda
Tutorial de como visualizar datos de COVID19 en Bokeh
Utilizing trajectories to find risk of geographical areas being infected by COVID-19 (PostgreSQL/PostGIS approach)
NCKU Operations Research Applications course - GitHub Writings
Repository created during Data Glacier internship
Implementation of VRS and CRS models of Data Envelopment Analysis, as well as robust DEA
ANN Geographic Segmentation Model to tell which of the customers are at highest risk of leaving
material desarrollado en el curso de deep learning de la UA
UCLA Master of Applied Economics Econ 413 Assignment
Machine Learning based AI to determine ease of doing business in various countries
The Economic Simulation Library provides an extensive collection of tools to develop, test, analyse and calibrate economic and financial agent-based models. The library is designed to take advantage of different computer architectures. In order to facilitate rapid iteration during model development the library can use parallel computation. Economic models developed using the library can be deployed into large-scale distributed computing environments when working with large model instances and datasets and provides routines to set up large-scale sampling computations during the analysis and calibration process.
redes neuronales en R
Repos for examples of abcEconomics simulations that can be extended from
Repo for html hosting (embed data studio)
Cluster + xboost for market selection
clustering plus xboost
algunos códigos abiertos de moondi
scraper winemag to csv
repositorio de las clases de aprendizaje automático del máster de robótica- ejercicios de clases