In this paper, we propose to use the concept of local fairness for auditing and ranking redistricting plans.

When auditing a redistricting plan, a persuasive method is to compare the plan with an ensemble of neutrally drawn redistricting plans. Ensembles are generated via algorithms that sample distributions on balanced graph partitions. To audit the partisan difference between the ensemble and a given plan, one must ensure that the non-partisan criteria are matched so that we may conclude that partisan differences come from bias rather than, for example, levels of compactness or differences in community preservation. Certain sampling algorithms allow one to explicitly state the policy-based probability distribution on plans, however, these algorithms have shown poor mixing times for large graphs (i.e. redistricting spaces) for all but a few specialized measures. In this work, we generate a multiscale parallel tempering approach that makes local moves at each scale. The local moves allow us to adopt a wide variety of policy-based measures. We examine our method in the state of Connecticut and succeed at achieving fast mixing on a policy-based distribution that has never before been sampled at this scale. Our algorithm shows promise to expand to a significantly wider class of measures that will (i) allow for more principled and situation-based comparisons and (ii) probe for the typical partisan impact that policy can have on redistricting.

Schneider Electric has officially commenced its digital transformation journey with Queen's Wharf Brisbane after two years' preparation. As a technology partner for the high-profile development, Schneider is set to future-proof the precinct with its cutting-edge technology in digital buildings and unrivalled local resources. Currently the largest development in Queensland, worth $3.6 billion and covering over 26 hectares of land and water, the Queen's Wharf Development transforms a once underutilised area into a vibrant location of major significance to the Brisbane CBD's future plans. The partnership will see Schneider design and implement integrated digital solutions that feature Building Management Systems (BMS), and Integrated System Platforms (ISP) across the whole precinct, including The Star Grand hotel, casino, main podium area, Sky Deck, as well as the Dorsett hotel and Rosewood hotel. Louise Monger, Vice President of Digital Buildings at Schneider Electric said, "We are delighted to have the opportunity to apply Schneider's world-class expertise in digital buildings to future proof such a significant project for the community. "Our relationship with the Queen's Wharf team began in 2017, when we first identified technology to be a key focus for the development.

We consider a problem of ecological inference, in which individual-level covariates are known, but labeled data is available only at the aggregate level. The intended application is modeling voter preferences in elections. In Rosenman and Viswanathan (2018), we proposed modeling individual voter probabilities via a logistic regression, and posing the problem as a maximum likelihood estimation for the parameter vector beta. The likelihood is a Poisson binomial, the distribution of the sum of independent but not identically distributed Bernoulli variables, though we approximate it with a heteroscedastic Gaussian for computational efficiency. Here, we extend the prior work by proving results about the existence of the MLE and the curvature of this likelihood, which is not log-concave in general. We further demonstrate the utility of our method on a real data example. Using data on voters in Morris County, NJ, we demonstrate that our approach outperforms other ecological inference methods in predicting a related, but known outcome: whether an individual votes.

When a syringe-wielding drill thief tried sticking up a Home Depot near Yankee Stadium, police figured out quickly that it wasn't a one-off. A man had also used a syringe a few weeks earlier while stealing a drill at another Home Depot 7 miles (11 kilometers) south in Manhattan. The match, though, wasn't made by an officer looking through files. It was done by pattern-recognition computer software developed by the New York Police Department. The software, dubbed Patternizr, allows crime analysts stationed in each of the department's 77 precincts to compare robberies, larcenies and thefts to hundreds of thousands of crimes logged in the NYPD's database, transforming their hunt for crime patterns with the click of a button.

When a syringe-wielding drill thief tried sticking up a Home Depot near Yankee Stadium, police figured out quickly that it wasn't a one-off. A man had also used a syringe a few weeks earlier while stealing a drill at another Home Depot 7 miles south in Manhattan. The match, though, wasn't made by an officer looking through files. It was done by pattern-recognition computer software developed by the New York Police Department. The software, dubbed Patternizr, allows crime analysts stationed in each of the department's 77 precincts to compare robberies, larcenies and thefts to hundreds of thousands of crimes logged in the NYPD's database, transforming their hunt for crime patterns with the click of a button.

NEW YORK - When a syringe-wielding drill thief tried sticking up a Home Depot near Yankee Stadium, police figured out quickly that it wasn't a one-off. A man had also used a syringe a few weeks earlier while stealing a drill at another Home Depot 7 miles (11 km) south in Manhattan. The match, though, wasn't made by an officer looking through files. It was done by pattern-recognition computer software developed by the New York Police Department. The software, dubbed Patternizr, allows crime analysts stationed in each of the department's 77 precincts to compare robberies, larcenies and thefts to hundreds of thousands of crimes logged in the NYPD's database, transforming their hunt for crime patterns with the click of a button.

The method used to arrive at this conclusion is really more fascinating than the answer and provides, perhaps, a view into the ways Big Data will in the future be used to understand all types of consumer preferences to inform marketing decisions and how the information trail we all leave behind online and in our driveways enlightens artificial intelligence (AI). Researchers recently reported how they taught and then used AI to scrutinise 50 million Google Street View images to find 22 million cars to build more than 2,600 automobile categories to find out if you voted Democrat or Republican. The idea was to learn if socioeconomic status and political persuasion could be gleaned from identifying what was parked in your driveway. Two weeks after putting the question to the AI, researchers could accurately predict if a community would vote Democrat or Republican just by looking at parked cars. Communities with a preponderance of sedans had an 88% chance of voting Democrat; neighbourhoods with extended cab pick-ups had an 82% chance of voting Republican.

Threshold tests have recently been proposed as a useful method for detecting bias in lending, hiring, and policing decisions. For example, in the case of credit extensions, these tests aim to estimate the bar for granting loans to white and minority applicants, with a higher inferred threshold for minorities indicative of discrimination. This technique, however, requires fitting a complex Bayesian latent variable model for which inference is often computationally challenging. Here we develop a method for fitting threshold tests that is two orders of magnitude faster than the existing approach, reducing computation from hours to minutes. To achieve these performance gains, we introduce and analyze a flexible family of probability distributions on the interval [0, 1] -- which we call discriminant distributions -- that is computationally efficient to work with. We demonstrate our technique by analyzing 2.7 million police stops of pedestrians in New York City.