A reinforcement learning approach to improve the performance of the Avellaneda-Stoikov market-making algorithm.

Market making is a high-frequency trading problem for which solutions based on reinforcement learning (RL) are being explored increasingly. This paper presents an approach to market making using deep reinforcement learning, with the novelty that, rather than to set the bid and ask prices directly, the neural network output is used to tweak the risk aversion parameter and the output of the Avellaneda-Stoikov procedure to obtain bid and ask prices that minimise inventory risk. Two further contributions are, first, that the initial parameters for the Avellaneda-Stoikov equations are optimised with a genetic algorithm, which parameters are also used to create a baseline Avellaneda-Stoikov agent (Gen-AS); and second, that state-defining features forming the RL agent's neural network input are selected based on their relative importance by means of a random forest. Two variants of the deep RL model (Alpha-AS-1 and Alpha-AS-2) were backtested on real data (L2 tick data from 30 days of bitcoin-dollar pair trading) alongside the Gen-AS model and two other baselines. The performance of the five models was recorded through four indicators (the Sharpe, Sortino and P&L-to-MAP ratios, and the maximum drawdown). Gen-AS outperformed the two other baseline models on all indicators, and in turn the two Alpha-AS models substantially outperformed Gen-AS on Sharpe, Sortino and P&L-to-MAP. Localised excessive risk-taking by the Alpha-AS models, as reflected in a few heavy dropdowns, is a source of concern for which possible solutions are discussed.

Obstructive Sleep Apnea in Women: Study of Speech and Craniofacial Characteristics.

BACKGROUND: Obstructive sleep apnea (OSA) is a common sleep disorder characterized by frequent cessation of breathing lasting 10 seconds or longer. The diagnosis of OSA is performed through an expensive procedure, which requires an overnight stay at the hospital. This has led to several proposals based on the analysis of patients' facial images and speech recordings as an attempt to develop simpler and cheaper methods to diagnose OSA. OBJECTIVE: The objective of this study was to analyze possible relationships between OSA and speech and facial features on a female population and whether these possible connections may be affected by the specific clinical characteristics in OSA population and, more specifically, to explore how the connection between OSA and speech and facial features can be affected by gender. METHODS: All the subjects are Spanish subjects suspected to suffer from OSA and referred to a sleep disorders unit. Voice recordings and photographs were collected in a supervised but not highly controlled way, trying to test a scenario close to a realistic clinical practice scenario where OSA is assessed using an app running on a mobile device. Furthermore, clinical variables such as weight, height, age, and cervical perimeter, which are usually reported as predictors of OSA, were also gathered. Acoustic analysis is centered in sustained vowels. Facial analysis consists of a set of local craniofacial features related to OSA, which were extracted from images after detecting facial landmarks by using the active appearance models. To study the probable OSA connection with speech and craniofacial features, correlations among apnea-hypopnea index (AHI), clinical variables, and acoustic and facial measurements were analyzed. RESULTS: The results obtained for female population indicate mainly weak correlations (r values between .20 and .39). Correlations between AHI, clinical variables, and speech features show the prevalence of formant frequencies over bandwidths, with F2/i/ being the most appropriate formant frequency for OSA prediction in women. Results obtained for male population indicate mainly very weak correlations (r values between .01 and .19). In this case, bandwidths prevail over formant frequencies. Correlations between AHI, clinical variables, and craniofacial measurements are very weak. CONCLUSIONS: In accordance with previous studies, some clinical variables are found to be good predictors of OSA. Besides, strong correlations are found between AHI and some clinical variables with speech and facial features. Regarding speech feature, the results show the prevalence of formant frequency F2/i/ over the rest of features for the female population as OSA predictive feature. Although the correlation reported is weak, this study aims to find some traces that could explain the possible connection between OSA and speech in women. In the case of craniofacial measurements, results evidence that some features that can be used for predicting OSA in male patients are not suitable for testing female population.

Reviewing the connection between speech and obstructive sleep apnea.

BACKGROUND: Sleep apnea (OSA) is a common sleep disorder characterized by recurring breathing pauses during sleep caused by a blockage of the upper airway (UA). The altered UA structure or function in OSA speakers has led to hypothesize the automatic analysis of speech for OSA assessment. In this paper we critically review several approaches using speech analysis and machine learning techniques for OSA detection, and discuss the limitations that can arise when using machine learning techniques for diagnostic applications. METHODS: A large speech database including 426 male Spanish speakers suspected to suffer OSA and derived to a sleep disorders unit was used to study the clinical validity of several proposals using machine learning techniques to predict the apnea-hypopnea index (AHI) or classify individuals according to their OSA severity. AHI describes the severity of patients' condition. We first evaluate AHI prediction using state-of-the-art speaker recognition technologies: speech spectral information is modelled using supervectors or i-vectors techniques, and AHI is predicted through support vector regression (SVR). Using the same database we then critically review several OSA classification approaches previously proposed. The influence and possible interference of other clinical variables or characteristics available for our OSA population: age, height, weight, body mass index, and cervical perimeter, are also studied. RESULTS: The poor results obtained when estimating AHI using supervectors or i-vectors followed by SVR contrast with the positive results reported by previous research. This fact prompted us to a careful review of these approaches, also testing some reported results over our database. Several methodological limitations and deficiencies were detected that may have led to overoptimistic results. CONCLUSION: The methodological deficiencies observed after critically reviewing previous research can be relevant examples of potential pitfalls when using machine learning techniques for diagnostic applications. We have found two common limitations that can explain the likelihood of false discovery in previous research: (1) the use of prediction models derived from sources, such as speech, which are also correlated with other patient characteristics (age, height, sex,…) that act as confounding factors; and (2) overfitting of feature selection and validation methods when working with a high number of variables compared to the number of cases. We hope this study could not only be a useful example of relevant issues when using machine learning for medical diagnosis, but it will also help in guiding further research on the connection between speech and OSA.

Speech Signal and Facial Image Processing for Obstructive Sleep Apnea Assessment.

Obstructive sleep apnea (OSA) is a common sleep disorder characterized by recurring breathing pauses during sleep caused by a blockage of the upper airway (UA). OSA is generally diagnosed through a costly procedure requiring an overnight stay of the patient at the hospital. This has led to proposing less costly procedures based on the analysis of patients' facial images and voice recordings to help in OSA detection and severity assessment. In this paper we investigate the use of both image and speech processing to estimate the apnea-hypopnea index, AHI (which describes the severity of the condition), over a population of 285 male Spanish subjects suspected to suffer from OSA and referred to a Sleep Disorders Unit. Photographs and voice recordings were collected in a supervised but not highly controlled way trying to test a scenario close to an OSA assessment application running on a mobile device (i.e., smartphones or tablets). Spectral information in speech utterances is modeled by a state-of-the-art low-dimensional acoustic representation, called i-vector. A set of local craniofacial features related to OSA are extracted from images after detecting facial landmarks using Active Appearance Models (AAMs). Support vector regression (SVR) is applied on facial features and i-vectors to estimate the AHI.