杏吧论坛

Abstract: We develop an equilibrium model for market impact of trades when investors with private signals execute via a trading desk. Fat tails in the distribution of the fundamental value lead to apower law forprice impact, while the impact is logarithmic for lighter tails. Moreover, the tail distribution of the equilibrium trade volume obeys a power law, consistent with numerous empirical studies. The spread decreases with the degree of noise trading and increases with the number of insiders. However, competition among insiders leads to aggressive trading, hence vanishing profit in the limit. The model also predicts that the order book flattens as the amount of noise trading increases converging to a model with proportional transaction costs with non-vanishing spread.

Take a look at Umut's slides (PDF).

Abstract: This talk will introduce the problem of parallel sequential change detection, which receives wide real-world applications in education, marketing, and cloud computing, among many others. This problem concerns detecting change points in parallel data streams, where each stream has its own change point,at which its data has a distributional change. With sequentially observed data, a decision-maker needs to declare whether changes have already occurred to the streams at each time point. Once a stream is declared to have changed, the decision-maker will intervene, such as deactivating the stream so that its future data will no longer be collected. We argue that for many applications, it is more sensible to optimise certain compound performance metrics that aggregate over all the streams. Consequently, the decisions for different streams become dependent. We propose a general compound decision framework for parallel sequential change detection, under which different performance metrics are given. In addition, data-driven decision procedures are developed, and optimality results are established for them. Some simulation results will be given to show the power of the proposed method.

Take a look at Yunxiao's slides (PDF).

Abstract: Dynamic term structure models offer standard tools for pricing and forecasting bond excess returns. A critical aspect of the process is to impose restrictions to tighten the link between cross-sectional and time-series variation of interest rates, and help resolve the puzzle of implausibly stable short-rate expectations. From a machine learning viewpoint the problem maybe cast as identifying the sparse signal of the market price of risk. We adopt a Bayesian approach to achieve sparsity utilising spike and slab priors to disentangle the signal from noise in bond risk premia. Our methodological framework successfully handles sequential model search by applying stochastic search variable selection (SSVS) over the restriction space landscape. At the same time, it can be linked with portfolio optimisation in real time, allowing investors to revise their beliefs when new information arrives. Empirical results reveal strong evidence of out-of-sample predictability in the case of sparse models that only allow level risk to be priced. Most importantly, such statistical evidence is turned into economically significant utility gains, across prediction horizons. Finally, the sequential version of the SSVS scheme, developed inthis work, offers an important diagnostic allowing to monitor potential changes over time spanning periods of macroeconomic uncertainty monetary policy changes.

Take a look at Kostas's slides (PDF).

Abstract: We consider latent variable models for the joint distribution of variables within a dyad of two interacting units, where the variables of interest are measured by multiple binary indicators. They are applied to analyse exchanges of practical and financial help between adult individuals and their non-coresident parents, using survey data from the UK Household Longitudinal Study. This is motivated by research questions in sociology and social policy about the levels of help given and on reciprocity between them. A particular focus here is on modelling the correlations between help given and received, and how they are associated with individual and family-level covariates. We implement the estimation of these models using a bespoke MCMC algorithm.

Take a look at Jouni's slides (PDF).

Abstract: A/B testing, or online experiment is a standard business strategy to compare a new product with an old one in pharmaceutical, technological, and traditional industries. Major challenges arise in online experiments of two-sided marketplace platforms (e.g.,Uber) where there is only one unit that receives a sequence of treatments over time. In those experiments, the treatment at a given time impacts current outcome as well as future outcomes. In this talk, we introduce a reinforcement learning framework for carrying A/B testing in these experiments, while characterizing the long-term treatment effects. Our proposed testing procedure allows for sequential monitoring and online updating. It is generally applicable to a variety of treatment designs in different industries. In addition, we systematically investigate the theoretical properties of our testing procedure. Finally, we apply our framework to both simulated data and a real-world data example obtained from a ridesharing company to illustrate its advantage over the current practice.

Take a look at Chengchun's slides (PDF).

Abstract: We introduce a new method for estimating the location of sparse changes in high-dimensional linear regression coefficients, without assuming that those coefficients are individually sparse. The procedure works by constructing different sketches (projections) of the design matrix at each time point, where consecutive projection matrices differ in sign in exactly one column. The sequence of sketched design matrices is then compared against a single sketched response vector to form a sequence of test statistics whose behaviour shows a surprising link to the well-known CUSUM statistics of univariate changepoint analysis. Strong theoretical guarantees are derived for the estimation accuracy of the procedure, which is computationally attractive, and simulations confirm that our methods perform well in a broad class of settings.

Take a look at Tengyao's slides (PDF).

Abstract: The aim of this project is to design and train a neural network for earthquake wave detection at Grillo seismic sensors. The goal is to train a neural network for recognition of the P-wave onset. The neural network trained is able to: Distinguish signal and noise sections. For signals, identify the P-wave arrival time with the precision of +5 seconds and identify the P-wave arrival time within 3 seconds after the P-wave arrival.

Take a look at Qixuan and Xixiang's slides (PDF).

Abstract: The frontier of healthcare has been shifting away from a one-size-fits all approach to delivering the best care for each person. In the era of big medical data, advanced analytics and technology, we at Roche are committed to creating and delivering data-driven, and/or technology-enabled innovations across the patient care continuum: from early detection and diagnosis, to remote care and monitoring. In this talk, we will share a few examples of Roche innovations in this space, our challenges and ambitions, and potential R&D ideas that welcome future collaborations.