Kelly-Based Options Trading Strategies on Settlement Date via Supervised Learning Algorithms

Computational Economics - Option is a well-known financial derivative that attracts attention from investors and scholars, due to its flexible investment strategies. In this paper, we sought to...     

Privacy-Preserving Data Communication Through Secure Multi-Party Computation in Healthcare Sensor Cloud

In recent years, wireless medical sensor networks meet the web to enable exciting healthcare applications that require data communication over the Internet. Often these applications suffer from data disclosure due to malicious users’ activities. To prevent such data disclosure in the healthcare systems, many public key cryptographic techniques have been used. However, most of them are too expensive to implement in the web-enabled wireless medical sensor networks. In 2013, Xun et al. introduced a lightweight encryption algorithm to protect communication between the sensor node and the data servers. Their scheme is based on the Sharemind framework. However, Sharemind framework has a limitation on the number of data storage servers (ie., three servers only). In addition, Xun et al’s scheme does not support privacy-preserving patient data analysis for distributed databases of different hospitals. In this paper, we introduce a new practical approach to prevent data disclosure from inside attack. Our new proposal is based on FairplayMP framework which enables programmers who are not experts in the theory of secure computation to implement such protocols. In addition, it support any number of n participants and is suitable for distributed environments. Moreover, in our new scheme, each sensor node needs only one secret key stored in advance to communicate with n different data servers, whereas three secret keys are embedded in advance into each sensor in order to communicate with three data servers in Xun et al’s scheme.     

Trading decryption for speeding encryption in Rebalanced-RSA

In 1982, Quisquater and Couvreur proposed an RSA variant, called RSA-CRT, based on the Chinese Remainder Theorem to speed up RSA decryption. In 1990, Wiener suggested another RSA variant, called Rebalanced-RSA, which further speeds up RSA decryption by shifting decryption costs to encryption costs. However, this approach essentially maximizes the encryption time since the public exponent e is generally about the same order of magnitude as the RSA modulus. In this paper, we introduce two variants of Rebalanced-RSA in which the public exponent e is much smaller than the modulus, thus reducing the encryption costs, while still maintaining low decryption costs. For a 1024-bit RSA modulus, our first variant (Scheme A) offers encryption times that are at least 2.6 times faster than that in the original Rebalanced-RSA, while the second variant (Scheme B) offers encryption times at least 3 times faster. In both variants, the decrease in encryption costs is obtained at the expense of slightly increased decryption costs and increased key generation costs. Thus, the variants proposed here are best suited for applications which require low costs in encryption and decryption.     

Top-k dominating queries on incomplete large dataset

Top-k dominating (TKD) query is one of the methods to find the interesting objects by returning the k objects that dominate other objects in a given dataset. Incomplete datasets have missing values in uncertain dimensions, so it is difficult to obtain useful information with traditional data mining methods on complete data. BitMap Index Guided Algorithm (BIG) is a good choice for solving this problem. However, it is even harder to find top-k dominance objects on incomplete big data. When the dataset is too large, the requirements for the feasibility and performance of the algorithm will become very high. In this paper, we proposed an algorithm to apply MapReduce on the whole process with a pruning strategy, called Efficient Hadoop BitMap Index Guided Algorithm (EHBIG). This algorithm can realize TKD query on incomplete datasets through BitMap Index and use MapReduce architecture to make TKD query possible on large datasets. By using the pruning strategy, the runtime and memory usage are greatly reduced. What’s more, we also proposed an improved version of EHBIG (denoted as IEHBIG) which optimizes the whole algorithm flow. Our in-depth work in this article culminates with some experimental results that clearly show that our proposed algorithm can perform well on TKD query in an incomplete large dataset and shows great performance in a Hadoop computing cluster.

     

Portfolio management system in equity market neutral using reinforcement learning

Portfolio management involves position sizing and resource allocation. Traditional and generic portfolio strategies require forecasting of future stock prices as model inputs, which is not a trivial task since those values are difficult to obtain in the real-world applications. To overcome the above limitations and provide a better solution for portfolio management, we developed a Portfolio Management System (PMS) using reinforcement learning with two neural networks (CNN and RNN). A novel reward function involving Sharpe ratios is also proposed to evaluate the performance of the developed systems. Experimental results indicate that the PMS with the Sharpe ratio reward function exhibits outstanding performance, increasing return by 39.0% and decreasing drawdown by 13.7% on average compared to the reward function of trading return. In addition, the proposed PMS_CNN model is more suitable for the construction of a reinforcement learning portfolio, but has 1.98 times more drawdown risk than the PMS_RNN. Among the conducted datasets, the PMS outperforms the benchmark strategies in TW50 and traditional stocks, but is inferior to a benchmark strategy in the financial dataset. The PMS is profitable, effective, and offers lower investment risk among almost all datasets. The novel reward function involving the Sharpe ratio enhances performance, and well supports resource-allocation for empirical stock trading.