Wei Huang

Recognizing the importance of jump risk in option pricing, we propose a neural jump stochastic differential equation model in this paper, which integrates neural networks as parameter estimators in the conventional jump diffusion model. To overcome the problem that the backpropagation algorithm is not compatible with the jump process, we use the Gumbel-Softmax method to make the jump parameter gradient learnable. We examine the proposed model using both simulated data and S&P 500 index options. The findings demonstrate that the incorporation of neural jump components substantially improves the accuracy of pricing compared to existing benchmark models.

AI technology has been introduced on ecommerce live-streaming as a substitute for human presenters who are expensive and constrained by work time. However, the cartoon avatar AI presenters that are commonly used today are less effective in driving sales. We propose that increasing human likeness is a practical method to boost sales, particularly for products with hedonic values and rich sensory attributes. The results show that a digital human presenter (an AI agent with a highly human realistic face and voice) sold better compared to a cartoon avatar presenter across a range of different types of products, and that this effect is driven both by affect (by increasing positive emotions) and cognition (by improving product quality evaluations). We extend current research on AI agent design to the livestreaming context and show that the highly realistic appearance of digital humans, as a powerful design, can enhance positive consumer responses to AI agents through two parallel theoretical routes (emotional and cognitive). These results can help e-commerce platforms and brands improve their AI technology and obtain expected business benefits.

Unsupervised classification is used in credit risk assessment to reduce human resource costs and make informed decisions in the shortest possible time. Although several studies show that support vector machine-based methods have better performance in unlabeled datasets, several factors still negatively affect these models, such as unstable results due to random initialization, reduced effectiveness due to kernel dependencies, and noise points and outliers. This paper introduces an unsupervised classification method based on a fuzzy unsupervised quadratic surface support vector machine without a kernel to avoid selecting related kernel parameters for credit risk assessment. In addition, we propose an innovative fuzzy membership function for reducing noise points and outliers in line with the direction of sample density variation. Fuzzy Unsupervised QSSVM (FUS-QSSVM) outperforms well-known SVM-based methods based on numerical tests on public benchmark credit data. In some real-world applications, the proposed method has significant potential as well as being effective, efficient, and robust. The algorithm can therefore increase the number of potential customers of financial institutions as well as increase profitability.

Data valuation, especially quantifying data value in algorithmic prediction and decision-making, is a fundamental problem in data trading scenarios. The most widely used method is to define the data Shapley and approximate it by means of the permutation sampling algorithm. To make up for the large estimation variance of the permutation sampling that hinders the development of the data marketplace, we propose a more robust data valuation method using stratified sampling, named variance reduced data Shapley (VRDS for short). We theoretically show how to stratify, how many samples are taken at each stratum, and the sample complexity analysis of VRDS. Finally, the effectiveness of VRDS is illustrated in different types of datasets and data removal applications.

Emerging event-based social networks (EBSNs), such as Meetup, have grown rapidly and become popular in recent years. EBSNs differ from conventional social networks such as Facebook in that they not only involve online social interactions but also include offline, in-person interactions. Thus, EBSNs are naturally heterogeneous and possess more valuable social information. Group recommendations in EBSNs are typically only based on the interest information filled in by users, or friends’ group information. Both these methods may not well reflect users’ real intentions. In this study, we propose a recommender system to predict groups that may interest EBSN users, based on a novel heterogeneous augmented graph method and a random walk with restart algorithm. In this approach, online and offline social interactions are combined into a single heterogeneous augmented graph capturing all useful relationships, including user-to-group relationships, user-to-event relationships, user-to-attribute relationships, and group-to-attribute relationships, and among others. To our knowledge, this work is the first attempt to apply a random walk algorithm into group recommendation in EBSNs. Extensive experiments on Meetup datasets demonstrate that our proposed recommender system achieves better results in terms of recall, precision, F-Measure and MRR metrics in comparison with the other four commonly used algorithms, including random recommendation, interest-based recommendation, interest- and neighborhood-based recommendation, and Katz Centrality. The significant recommendation performance of our approach may further enhance user satisfaction of EBSNs. Moreover, our approach to group recommendation may also be extended to other recommendation-related applications such as event or friend recommendation.

Background: The SARS-COV-2 virus and its variants pose extraordinary challenges for public health worldwide. Timely and accurate forecasting of the COVID-19 epidemic is key to sustaining interventions and policies and efficient resource allocation. Internet-based data sources have shown great potential to supplement traditional infectious disease surveillance, and the combination of different Internet-based data sources has shown greater power to enhance epidemic forecasting accuracy than using a single Internet-based data source. However, existing methods incorporating multiple Internet-based data sources only used real-time data from these sources as exogenous inputs but did not take all the historical data into account. Moreover, the predictive power of different Internet-based data sources in providing early warning for COVID-19 outbreaks has not been fully explored. Objective: The main aim of our study is to explore whether combining real-time and historical data from multiple Internet-based sources could improve the COVID-19 forecasting accuracy over the existing baseline models. A secondary aim is to explore the COVID-19 forecasting timeliness based on different Internet-based data sources. Methods: We first used core terms and symptom-related keyword-based methods to extract COVID-19–related Internet-based data from December 21, 2019, to February 29, 2020. The Internet-based data we explored included 90,493,912 online news articles, 37,401,900 microblogs, and all the Baidu search query data during that period. We then proposed an autoregressive model with exogenous inputs, incorporating real-time and historical data from multiple Internet-based sources. Our proposed model was compared with baseline models, and all the models were tested during the first wave of COVID-19 epidemics in Hubei province and the rest of mainland China separately. We also used lagged Pearson correlations for COVID-19 forecasting timeliness analysis. Results: Our proposed model achieved the highest accuracy in all 5 accuracy measures, compared with all the baseline models of both Hubei province and the rest of mainland China. In mainland China, except for Hubei, the COVID-19 epidemic forecasting accuracy differences between our proposed model (model i) and all the other baseline models were statistically significant (model 1, t198=–8.722, P<.001; model 2, t198=–5.000, P<.001, model 3, t198=–1.882, P=.06; model 4, t198=–4.644, P<.001; model 5, t198=–4.488, P<.001). In Hubei province, our proposed model's forecasting accuracy improved significantly compared with the baseline model using historical new confirmed COVID-19 case counts only (model 1, t198=–1.732, P=.09). Our results also showed that Internet-based sources could provide a 2- to 6-day earlier warning for COVID-19 outbreaks. Conclusions: Our approach incorporating real-time and historical data from multiple Internet-based sources could improve forecasting accuracy for epidemics of COVID-19 and its variants, which may help improve public health agencies' interventions and resource allocation in mitigating and controlling new waves of COVID-19 or other relevant epidemics.

BACKGROUND The SARS-COV-2 virus and its variants pose extraordinary challenges for public health worldwide. Timely and accurate forecasting of the COVID-19 epidemic is key to sustaining interventions and policies and efficient resource allocation. Internet-based data sources have shown great potential to supplement traditional infectious disease surveillance, and the combination of different Internet-based data sources has shown greater power to enhance epidemic forecasting accuracy than using a single Internet-based data source. However, existing methods incorporating multiple Internet-based data sources only used real-time data from these sources as exogenous inputs but did not take all the historical data into account. Moreover, the predictive power of different Internet-based data sources in providing early warning for COVID-19 outbreaks has not been fully explored. OBJECTIVE The main aim of our study is to explore whether combining real-time and historical data from multiple Internet-based sources could improve the COVID-19 forecasting accuracy over the existing baseline models. A secondary aim is to explore the COVID-19 forecasting timeliness based on different Internet-based data sources. METHODS We first used core terms and symptom-related keyword-based methods to extract COVID-19–related Internet-based data from December 21, 2019, to February 29, 2020. The Internet-based data we explored included 90,493,912 online news articles, 37,401,900 microblogs, and all the Baidu search query data during that period. We then proposed an autoregressive model with exogenous inputs, incorporating real-time and historical data from multiple Internet-based sources. Our proposed model was compared with baseline models, and all the models were tested during the first wave of COVID-19 epidemics in Hubei province and the rest of mainland China separately. We also used lagged Pearson correlations for COVID-19 forecasting timeliness analysis. RESULTS Our proposed model achieved the highest accuracy in all 5 accuracy measures, compared with all the baseline models of both Hubei province and the rest of mainland China. In mainland China, except for Hubei, the COVID-19 epidemic forecasting accuracy differences between our proposed model (model i) and all the other baseline models were statistically significant (model 1, t198=–8.722, P<.001; model 2, t198=–5.000, P<.001, model 3, t198=–1.882, P=.06; model 4, t198=–4.644, P<.001; model 5, t198=–4.488, P<.001). In Hubei province, our proposed model's forecasting accuracy improved significantly compared with the baseline model using historical new confirmed COVID-19 case counts only (model 1, t198=–1.732, P=.09). Our results also showed that Internet-based sources could provide a 2- to 6-day earlier warning for COVID-19 outbreaks. CONCLUSIONS Our approach incorporating real-time and historical data from multiple Internet-based sources could improve forecasting accuracy for epidemics of COVID-19 and its variants, which may help improve public health agencies' interventions and resource allocation in mitigating and controlling new waves of COVID-19 or other relevant epidemics.

Real-time online data sources have contributed to timely and accurate forecasting of influenza activities while also suffered from instability and linguistic noise. Few previous studies have focused on unofficial online news articles, which are abundant in their numbers, rich in information, and relatively low in noise. This study examined whether monitoring both official and unofficial online news articles can improve influenza activity forecasting accuracy during influenza outbreaks. Data were retrieved from a Chinese commercial online platform and the website of the Chinese National Influenza Center. We modeled weekly fractions of influenza-related online news articles and compared them against weekly influenza-like illness (ILI) rates using autoregression analyses. We retrieved 153,958,695 and 149,822,871 online news articles focusing on the south and north of mainland China separately from 6 October 2019 to 17 May 2020. Our model based on online news articles could significantly improve the forecasting accuracy, compared to other influenza surveillance models based on historical ILI rates (p = 0.002 in the south; p = 0.000 in the north) or adding microblog data as an exogenous input (p = 0.029 in the south; p = 0.000 in the north). Our finding also showed that influenza forecasting based on online news articles could be 1–2 weeks ahead of official ILI surveillance reports. The results revealed that monitoring online news articles could supplement traditional influenza surveillance systems, improve resource allocation, and offer models for surveillance of other emerging diseases.