Such models have been shown to allow estimation and inference by regression clustering methods. This paper is motivated by the finding that the clustered heterogeneity models studied in this literature can be badly misspecified, even when the panel has significant discrete cross-sectional structure. To address this issue, we generalize previous approaches to discrete unobserved heterogeneity by allowing each unit to have multiple, imperfectly-correlated latent variables that describe its response-type to different covariates. We give inference results for a k-means style estimator of our model and develop information criteria to jointly select the number clusters for each latent variable. Monte Carlo simulations confirm our theoretical results and give intuition about the finite-sample performance of estimation and model selection. We also contribute to the theory of clustering with an over-specified number of clusters and derive new convergence rates for this setting. Our results suggest that over-fitting can be severe in k-means style estimators when the number of clusters is over-specified.

When a mysterious illness first pops up, it can be difficult for governments and public health officials to gather information quickly and coordinate a response. But new artificial intelligence technology can automatically mine through news reports and online content from around the world, helping experts recognize anomalies that could lead to a potential epidemic or, worse, a pandemic. In other words, our new AI overlords might actually help us survive the next plague. These new AI capabilities are on full display with the recent coronavirus outbreak, which was identified early by a Canadian firm called BlueDot, which is one of a number of companies that use data to evaluate public health risks. The company, which says it conducts "automated infectious disease surveillance," notified its customers about the new form of coronavirus at the end of December, days before both the US Centers for Disease Control and Prevention (CDC) and the World Health Organization (WHO) sent out official notices, as reported by Wired.

Prior to AVIO Consulting, Slack was the Vice President of Sales and Marketing for Clevyr, who builds software solutions. Before that, he was the Director of Business Development for Hoegg Software. Slack's passion for tech also inspired him to co-create StarSpace46, a coworking space in Oklahoma City serving tech startups. AVIO has recently been recognized as one of the fastest-growing companies by the Inc. 5000 List, Consulting Magazine, and the SMU Cox Dallas 100, among others. Slack's hire was a result of AVIO's desire to keep building momentum for the firm's healthy growth with a clear and strategic vision.

We propose a new method for clustering multivariate time-series data based on Dynamic Linear Models. Whereas usual time-series clustering methods obtain static membership parameters, our proposal allows each time-series to dynamically change their cluster memberships over time. In this context, a mixture model is assumed for the time series and a flexible Dirichlet evolution for mixture weights allows for smooth membership changes over time. Posterior estimates and predictions can be obtained through Gibbs sampling, but a more efficient method for obtaining point estimates is presented, based on Stochastic Expectation-Maximization and Gradient Descent. Finally, two applications illustrate the usefulness of our proposed model to model both univariate and multivariate time-series: World Bank indicators for the renewable energy consumption of EU nations and the famous Gapminder dataset containing life-expectancy and GDP per capita for various countries.

Machine learning techniques have been paramount throughout the last years, being applied in a wide range of tasks, such as classification, object recognition, person identification, image segmentation, among others. Nevertheless, conventional classification algorithms, e.g., Logistic Regression, Decision Trees, Bayesian classifiers, might lack complexity and diversity, not being suitable when dealing with real-world data. A recent graph-inspired classifier, known as the Optimum-Path Forest, has proven to be a state-of-the-art technique, comparable to Support Vector Machines and even surpassing it in some tasks. In this paper, we propose a Python-based Optimum-Path Forest framework, denoted as OPFython, where all of its functions and classes are based upon the original C language implementation. Additionally, as OPFython is a Python-based library, it provides a more friendly environment and a faster prototyping workspace than the C language.

We introduce a random forest approach to enable spreads' prediction in the primary catastrophe bond market. We investigate whether all information provided to investors in the offering circular prior to a new issuance is equally important in predicting its spread. The whole population of non-life catastrophe bonds issued from December 2009 to May 2018 is used. The random forest shows an impressive predictive power on unseen primary catastrophe bond data explaining 93% of the total variability. For comparison, linear regression, our benchmark model, has inferior predictive performance explaining only 47% of the total variability. All details provided in the offering circular are predictive of spread but in a varying degree. The stability of the results is studied. The usage of random forest can speed up investment decisions in the catastrophe bond industry.

Noise reduction is an important part of modern hearing aids and is included in most commercially available devices. Deep learning-based state-of-the-art algorithms, however, either do not consider real-time and frequency resolution constrains or result in poor quality under very noisy conditions. To improve monaural speech enhancement in noisy environments, we propose CLCNet, a framework based on complex valued linear coding. First, we define complex linear coding (CLC) motivated by linear predictive coding (LPC) that is applied in the complex frequency domain. Second, we propose a framework that incorporates complex spectrogram input and coefficient output. Third, we define a parametric normalization for complex valued spectrograms that complies with low-latency and on-line processing. Our CLCNet was evaluated on a mixture of the EUROM database and a real-world noise dataset recorded with hearing aids and compared to traditional real-valued Wiener-Filter gains.

New research from the Global Talent Competitiveness Index 2020 confirms that to succeed in the age of AI, more investment is needed in skills development and lifelong learning. While the emerging markets lag far behind the talent-rich nations, the gap can be bridged with the right set of policies. The currency of the AI-driven economy is talent. But while it is true that talent is high in demand, it is also short in supply. This especially rings true for the economies that fail to attract and build their own talented workforces.

Providing your client with insights, briefly defined as short texts of analytically processed information, is a valuable addition to the services provided by virtually any company. Unfortunately, as engineers, or technicians in general, our training does not address in detail the techniques for writing insights. This short text seeks to serve as a basic guide for future analysts. I introduce the concept of insight and provide advice for the creation of concise and short intelligence pieces. As a senior data analyst, I must do precisely what Ray Dalio, finance magnate, mentions in his December 2019 conversation with Lex Fridman in his podcast "Artificial Intelligence" when asked what role machine learning will play in making decisions and in the analysis: TSC.ai (where I work as a Senior Data Analyst) is a technology company that uses articial intelligence to provide, precisely, intelligence to our customers.

NeurIPS 2019, the latest incarnation of the Neural Information Processing Systems conference, wrapped up just over a week ago. Multiple great blog posts have already summarized various talks and key trends, so the goal of this piece is more humble: to reflect on the experience of attending the conference, and in particular whether its vast size is harmful to its purpose as a research conference. Thirteen thousand attendees, 1,428 accepted papers, and 57 workshops vast. This is 9 minutes condensed down to 15 seconds, and this is not even close to all the attendees! Is that a Rolling Stones concert?