Search
Results
-
Interpretability and Explainability: A Machine Learning Zoo Mini-tour
(2020)In this review, we examine the problem of designing interpretable and explainable machine learning models. Interpretability and explainability lie at the core of many machine learning and statistical applications in medicine, economics, law, and natural sciences. Although interpretability and explainability have escaped a clear universal definition, many techniques motivated by these properties have been developed over the recent 30 years ...Working Paper -
A Safe Harbor: Wealth-Income Ratios in Switzerland over the 20th Century and the Role of Housing Prices
(2020)KOF Working PapersWe estimate the ratio of private wealth to national income, βpt, for Switzerland over the period 1900–2018. Our results indicate that the development of βpt in Switzerland did not follow a U-shaped pattern as in most European countries, but that the evolution was extraordinarily stable, with βpt oscillating around 500% over most of the 20th century. However, the wealth-income ratio has been on the rise since the turn of the century to ...Working Paper -
Adaptive Extreme Edge Computing for Wearable Devices
(2020)arXivWearable devices are a fast-growing technology with impact on personal healthcare for both society and economy. Due to the widespread of sensors in pervasive and distributed networks, power consumption, processing speed, and system adaptation are vital in future smart wearable devices. The visioning and forecasting of how to bring computation to the edge in smart sensors have already begun, with an aspiration to provide adaptive extreme ...Working Paper -
-
Regional Borders, Commuting and Transport Network Integration
(2020)KOF Working PapersI study how and why economic activity varies around regional borders. Spatial quasi-experimental variation around French departmental borders reveals discontinuous commuting and residential patterns. To tackle the endogenous border placement problem, I exploit a geometric border design proposed during the French Revolution. I then calibrate a spatial quantifiable general equilibrium framework to structurally match the quasi-experimental ...Working Paper -
Tracking Economic Activity With Alternative High-Frequency Data
(2020)KOF Working PapersMost macroeconomic indicators failed to capture the sharp economic fluctuations dur- ing the Corona crisis in a timely manner. Instead, alternative high-frequency data have been used, aiming to monitor the economic situation. However, these data are often only loosely related to the business cycle and come with irregular patterns of missing observations, ragged edges and short histories. This paper presents a novel mixed- frequency dynamic ...Working Paper -
In-store or online grocery shopping before and during the COVID-19 pandemic
(2020)Arbeitsberichte Verkehrs- und RaumplanungThis paper presents results of a stated choice (SC) experiment to uncover the determinants of grocery shopping channel choice during this first wave of widespread COVID-19 infections where the most restrictive containment measures were in place, making the dataset unique. The choice sets were framed under regular and pandemic conditions, allowing the estimation of pandemic-specific effects for each of the choice attributes. Our results ...Working Paper -
Ride-pooling efficiency in large, medium-sized and small towns
(2020)Arbeitsberichte Verkehrs- und RaumplanungThis study introduces an autonomous ride-pooling service to six communities with varying population sizes and trip densities in the Munich Metropolitan Region. We investigate a laissez-faire scenario without additional policies, defining the modal shift through an incremental mode choice model. Additionally, a draconian scenario in which each within- city car trip is replaced by ride-pooling is analyzed. Results indicate a logarithmic ...Working Paper -
The Universal Approximation Property
(2020)arXivThe universal approximation property of various machine learning models is currently only understood on a case-by-case basis, limiting the rapid development of new theoretically justified neural network architectures and blurring our understanding of our current models' potential. This paper works towards overcoming these challenges by presenting a characterization, a representation, a construction method, and an existence result, each ...Working Paper -
Open data travel demand synthesis for agent-based transport simulation
(2020)Arbeitsberichte Verkehrs- und RaumplanungSynthetic populations of travellers and their detailed mobility behaviour are an important basis for agent-based transport simulations, which are increasingly used in transport planning and research today. While previous applications of such simulations put focus on analyzing policies and novel modes of transport, less importance is put on the aspects of data collection, processing and validation to create the disaggregate travel demand. ...Working Paper