Search
Now showing items 1-10 of 30
FairML : ToolBox for diagnosing bias in predictive modeling
(Massachusetts Institute of Technology, 2016)
Predictive models are increasingly deployed for the purpose of determining access to services such as credit, insurance, and employment. Despite societal gains in efficiency and productivity through deployment of these ...
Discrimination, fairness and prediction in policing : fare evasion in New York City
(Massachusetts Institute of Technology, 2020)
Predictive policing has quickly become widespread in the United States. Practitioners claim it can greatly increase police efficiency and base decisions on objective statistics. Critics say that these algorithms reproduce ...
Transfer learning for predictive models in MOOCs
(Massachusetts Institute of Technology, 2016)
Predictive models are crucial in enabling the personalization of student experiences in Massive Open Online Courses. For successful real-time interventions, these models must be transferable - that is, they must perform ...
Learning from supply shocks in the energy market : evidence from local and global impacts of the shale revolution
(Massachusetts Institute of Technology, 2020)
In this thesis, we carry out three studies of the local and global impacts of supply shocks in energy markets, and also analyze certain properties of these markets. First, the relationship between US power plants and local ...
Optimal sizing of solar and battery assets in decentralized micro-grids with demand-side management
(Massachusetts Institute of Technology, 2017)
Solar-based community micro-grids and individual home systems have been recognized as key enablers of electricity provision to the over one billion people living without energy access to-date. Despite significant cost ...
Networked interactions, graphical models and econometrics perspectives in data analysis
(Massachusetts Institute of Technology, 2020)
This thesis is composed of two independent parts. In Part I, we study higher-order interactions in both graphical models and networks, i.e., interactions between more than two nodes. In the graphical model setting, we do ...
Privacy-preserving identity transactions online : the use case of brokered identity federations
(Massachusetts Institute of Technology, 2021)
Disinformation campaigns, created by fake accounts on online community platforms, have grown into one of the biggest threats against democracy, freedom and user perception of the truth. This thesis argues that mitigating ...
Adaptive electricity access planning
(Massachusetts Institute of Technology, 2018)
About 1.1 billion people worldwide lack access to electricity and an additional 1 billion have unreliable access. The social ramifications of this problem are noteworthy because access to electric power has the potential ...
Design and validation of mobile kit and machine learning algorithms for pulmonary disease screening and diagnosis
(Massachusetts Institute of Technology, 2017)
Pulmonary diseases are responsible for more than 15% of deaths worldwide. Much of this burden is concentrated in the developing world, where these diseases cause 19% of deaths. In much of the developing world, pulmonary ...
Understanding the institutional landscape of cyber security
(Massachusetts Institute of Technology, 2016)
The decentralized architecture of the Internet, which has been key to its development and worldwide deployment, is making it challenging to secure Internet user experience. Many organizations claim to be playing a role in ...