Best practices for portfolio optimization by quantum computing, experimented on real quantum devices.

In finance, portfolio optimization aims at finding optimal investments maximizing a trade-off between return and risks, given some constraints. Classical formulations of this quadratic optimization problem have exact or heuristic solutions, but the complexity scales up as the market dimension increases. Recently, researchers are evaluating the possibility of facing the complexity scaling issue by employing quantum computing. In this paper, the problem is solved using the Variational Quantum Eigensolver (VQE), which in principle is very efficient. The main outcome of this work consists of the definition of the best hyperparameters to set, in order to perform Portfolio Optimization by VQE on real quantum computers. In particular, a quite general formulation of the constrained quadratic problem is considered, which is translated into Quadratic Unconstrained Binary Optimization by the binary encoding of variables and by including constraints in the objective function. This is converted into a set of quantum operators (Ising Hamiltonian), whose minimum eigenvalue is found by VQE and corresponds to the optimal solution. In this work, different hyperparameters of the procedure are analyzed, including different ansatzes and optimization methods by means of experiments on both simulators and real quantum computers. Experiments show that there is a strong dependence of solutions quality on the sufficiently sized quantum computer and correct hyperparameters, and with the best choices, the quantum algorithm run on real quantum devices reaches solutions very close to the exact one, with a strong convergence rate towards the classical solution, even without error-mitigation techniques. Moreover, results obtained on different real quantum devices, for a small-sized example, show the relation between the quality of the solution and the dimension of the quantum processor. Evidences allow concluding which are the best ways to solve real Portfolio Optimization problems by VQE on quantum devices, and confirm the possibility to solve them with higher efficiency, with respect to existing methods, as soon as the size of quantum hardware will be sufficiently high.

An Effective BERT-Based Pipeline for Twitter Sentiment Analysis: A Case Study in Italian.

Over the last decade industrial and academic communities have increased their focus on sentiment analysis techniques, especially applied to tweets. State-of-the-art results have been recently achieved using language models trained from scratch on corpora made up exclusively of tweets, in order to better handle the Twitter jargon. This work aims to introduce a different approach for Twitter sentiment analysis based on two steps. Firstly, the tweet jargon, including emojis and emoticons, is transformed into plain text, exploiting procedures that are language-independent or easily applicable to different languages. Secondly, the resulting tweets are classified using the language model BERT, but pre-trained on plain text, instead of tweets, for two reasons: (1) pre-trained models on plain text are easily available in many languages, avoiding resource- and time-consuming model training directly on tweets from scratch; (2) available plain text corpora are larger than tweet-only ones, therefore allowing better performance. A case study describing the application of the approach to Italian is presented, with a comparison with other Italian existing solutions. The results obtained show the effectiveness of the approach and indicate that, thanks to its general basis from a methodological perspective, it can also be promising for other languages.

SARS-CoV-2 Infections and COVID-19 Fatality: Estimation of Infection Fatality Ratio and Current Prevalence.

COVID-19 is one of the most important problems for public health, according to the number of deaths associated to this pathology reported so far. However, from the epidemiological point of view, the dimension of the problem is still unknown, since the number of actual cases of SARS-CoV-2 infected people is underestimated, due to limited testing. This paper aims at estimating the actual Infection Fatality Ratio (number of deaths with respect to the number of infected people) and the actual current prevalence (number of infected people with respect to the entire population), both in a specific population and all over the world. With this aim, this paper proposes a method to estimate Infection Fatality Ratio of a still ongoing infection, based on a daily estimation, and on the relationship between this estimation and the number of tests performed per death. The method has been applied using data about COVID-19 from Italy. Results show a fatality ratio of about 0.9%, which is lower than previous findings. The number of actual infected people in Italy is also estimated, and results show that (i) infection started at the end of January 2020; (ii) a maximum number of about 100,000 new cases in one day was reached at the beginning of March 2020; (iii) the estimated cumulative number of infections at the beginning of October 2020 is about 4.2 million cases in Italy (more than 120 million worldwide, if a generalization is conjectured as reasonable). Therefore, the prevalence at the beginning of October 2020 is estimated at about 6.9% in Italy (1.6% worldwide, if a generalization is conjectured).

Early prediction of radiotherapy-induced parotid shrinkage and toxicity based on CT radiomics and fuzzy classification.

MOTIVATION: Patients under radiotherapy for head-and-neck cancer often suffer of long-term xerostomia, and/or consistent shrinkage of parotid glands. In order to avoid these drawbacks, adaptive therapy can be planned for patients at risk, if the prediction is obtained timely, before or during the early phase of treatment. Artificial intelligence can address the problem, by learning from examples and building classification models. In particular, fuzzy logic has shown its suitability for medical applications, in order to manage uncertain data, and to build transparent rule-based classifiers. In previous works, clinical, dosimetric and image-based features were considered separately, to find different possible predictors of parotid shrinkage. On the other hand, a few works reported possible image-based predictors of xerostomia, while the combination of different types of features has been little addressed. OBJECTIVE: This paper proposes the application of a novel machine learning approach, based on both statistics and fuzzy logic, aimed at the classification of patients at risk of i) parotid gland shrinkage and ii) 12-months xerostomia. Both problems are addressed with the aim of individuating predictors and models to classify respective outcomes. METHODS: Knowledge is extracted from a real dataset of radiotherapy patients, by means of a recently developed method named Likelihood-Fuzzy Analysis, based on the representation of statistical information by fuzzy rule-based models. This method enables to manage heterogeneous variables and missing data, and to obtain interpretable fuzzy models presenting good generalization power (thus high performance), and to measure classification confidence. Numerous features are extracted to characterize patients, coming from different sources, i.e. clinical features, dosimetric parameters, and radiomics-based measures obtained by texture analysis of Computed Tomography images. A learning approach based on the composition of simple models in a more complicated one allows to consider the features separately, in order to identify predictors and models to use when only some data source is available, and obtaining more accurate results when more information can be combined. RESULTS: Regarding parotid shrinkage, a number of good predictors is detected, some already known and confirmed here, and some others found here, in particular among radiomics-based features. A number of models are also designed, some using single features and others involving models composition to improve classification accuracy. In particular, the best model to be used at the initial treatment stage, and another one applicable at the half treatment stage are identified. Regarding 12-months toxicity, some possible predictors are detected, in particular among radiomics-based features. Moreover, the relation between final parotid shrinkage rate and 12-months xerostomia is evaluated. The method is compared to the naïve Bayes classifier, which reveals similar results in terms of classification accuracy and best predictors. The interpretable fuzzy rule-based models are explicitly presented, and the dependence between predictors and outcome is explained, thus furnishing in some cases helpful insights about the considered problems. CONCLUSION: Thanks to the performance and interpretability of the fuzzy classification method employed, predictors of both parotid shrinkage and xerostomia are detected, and their influence on each outcome is revealed. Moreover, models for predicting parotid shrinkage at initial and half radiotherapy stages are found.

Likelihood-fuzzy analysis of parotid gland shrinkage in radiotherapy patients.

In head-and-neck radiotherapy, an early detection of patients who will undergo parotid glands shrinkage during the treatment is of primary importance, since this condition has been found to be associated with acute toxicity. In this work, a recently proposed approach, here named Likelihood-Fuzzy Analysis, based on both statistical learning and Fuzzy Logic, is proposed to support the identification of early predictors of parotid shrinkage from Computed Tomography images acquired during radiotherapy. For this purpose, a set of textural image parameters was extracted and considered as candidate of parotid shrinkage prediction; for all these parameters and combinations of maximum three of them, a fuzzy rule base was extracted, gaining very good results in terms of accuracy, sensitivity and specificity. The performance of classification was also compared to a classical Fisher's Linear Discriminant Analysis and found to provide better results. Moreover, the use of Fuzzy Logic allowed obtaining an interpretable description of the relations between textural features and the shrinkage process.