Showing papers by "Mu-En Wu published in 2018"

Applied attention-based LSTM neural networks in stock prediction

Abstract: Prediction of stocks is complicated by the dynamic, complex, and chaotic environment of the stock market. Many studies predict stock price movements using deep learning models. Although the attention mechanism has gained popularity recently in neural machine translation, little focus has been devoted to attention-based deep learning models for stock prediction. This paper proposes an attention-based long short-term memory model to predict stock price movement and make trading strategies

A Novel Approach of Option Portfolio Construction Using the Kelly Criterion

Abstract: Money management is one of the most important issues in financial trading. Many skills of money managements are based on the Kelly criterion, which is a theoretical optimization of bidding an optimal fraction for position sizing. However, there is still a large gap between the theory and the real trading for money management. In this paper, we design an option trading strategy via Kelly criterion. While the price movements of options are highly volatile, various options’ portfolio can be formed by long or short at different strike prices to pre-lock the losses and profits; then we have a fixed profit and loss distribution via holding an option portfolio. Consequently, the Kelly criterion can be applied to the options’ trading for calculating the optimal bidding fraction. We propose a method for option trading, in finding the profitable option portfolio by bidding optimal fraction. Compared with prior works, our proposed model is a novel approach for options’ trading with the money management of position sizing. Experiments are conducted to show the feasibility and profitability of our method in practical scenarios. Future works are provided in the final section.

A shareable keyword search over encrypted data in cloud computing

Abstract: Cloud storage is one of the most important applications in our daily lives. User can store their own data into cloud storage and remotely access the saved data. Owing to the social media develops, users can share the digital files to other users, leading to the amount of data growing rapidly and searching abilities necessarily. In the some cases, servers cannot avoid data leakage even if the server provides complete access control. The encrypted data is a best way to resolve this problem but it may eliminate original structure and searching may become impossible. Applying searchable encryption for each receiver may produce messy duplication and occupy the quota of cloud storage from each receiver. User requires keeping their shared documents belonging up to date which are compared with the latest version. To this aim, we thus propose a sharable ID-based encryption with keyword search in cloud computing environment, which enables users to search in data owners’ shared storage while preserving privacy of data. For the performance analysis, we demonstrate the compared resultant with others ID-based or ID-relative encryption. In addition to that, we show the formal proof to verify the security of our proposed.

A Framework of Option Buy-Side Strategy with Simple Index Futures Trading Based on Kelly Criterion

Abstract: We propose a framework of option trading strategy for the simple index futures trading. According to Kelly criterion, we find the most profitable option strike price for buying side and calculate the optimal lots of option for position size. We hope this skill can be applied to any futures trading strategies by using option buy-side.

A Sophisticated Optimization Algorithm for Obtaining a Group Trading Strategy Portfolio and Its Stop-Loss and Take-Profit Points

Abstract: Due to the variety of financial markers, to determine an appropriate timing for buying or selling stocks is always a difficult task, the common way to handle it is using trading strategies formed by technical or fundamental indicators. To deal with the problem, an approach was proposed for optimizing a group trading strategy portfolio in the previous approach. To avoid unpredictable loss, the stop-loss and take-profit points are commonly used by investors to handle it. However, they are not easy determined by users when different trading strategies are employed. In this paper, attempting to provide a more useful group trading strategy portfolio, we propose an algorithm for obtaining a group trading strategy portfolio and its stop-loss and take-profit points using the grouping genetic algorithm. Experiments were conducted on a real dataset to reveal the effectiveness of the proposed approach.

Forged Seal Imprint Identification Based on Regression Analysis on Imprint Borders and Metrics Comparisons

Abstract: Verifying a seal imprint to authenticate the identity is a general and important task in financial industries. The seal imprint attached to a document is often used as a form of authenticity. Therefore, in financial applications, it is often necessary to recognize whether a seal is genuine or forged. In order to simplify the verification, we propose an effective method based on regression analysis to approximate the imprint borders, and use the geometric transformation to adjust the perspective of the detected imprint image. To align the detected image with the original image, the first step is to find four borders and cross each border to obtain four vertices of the rectangular imprints. The Ordinary Least Squares regression is then applied on the outer strong feature points, and the estimated regression line would be taken as the borders. The regression process is repeated several times to estimate border lines as precise as possible. Besides, considering the practical application in taking seal imprints by camera, the imprint is subject to geometric distortion, due to camera perspectives, comparing to the stored genuine imprint image. Therefore, the detected image is geometrically transformed to align its perspective with the genuine imprint. Finally, the SSIM and PSNR are calculated as the decision metrics to check whether the two indexes exceed the predetermined thresholds. Then the imprint is determined as a genuine or forged imprint. The experiments are conducted among various stamping imprints, and the results show the efficiency and effectiveness of the proposed identification approach.

A Novel Approach for Option Trading Based on Kelly Criterion

Abstract: An option trading model based on Kelly criterion is proposed in this work. Via longing and shorting options at different strike prices, various portfolio strategies which lock the losses and profits in advance can be formed; in other words, we hold a portfolio of options with a fixed profit and loss distribution. We design and use Kelly criterion applied to the options trading, in terms of calculating the optimal bidding fraction. In this paper we provide a model for developing an option trading system for finding the profitable option portfolio with optimal bidding fraction. This is a new approach for option trading with position management, and some future directions are provided.

Oblivious Transfer Protocols Based on Commutative Encryption

Abstract: Oblivious transfer (OT) protocol is a fundamental building block of cryptography and can be applied widely in many fields. A secure oblivious transfer protocol is supposed to ensure the privacy of both senders and receivers. The privacy of receivers means that the information being selected by receivers would never be revealed to senders. On the other hand, the privacy of senders means that receivers have no further information except for the one that has been selected. In this case, senders are able to deceive receivers by sending same messages. Likewise, in existing 1-out-of-n OT protocols, malicious senders can make all the n messages the same, so that receivers will always get the specific one assigned by senders. This indicates that privacy of receivers wouldnt work under the 1-out-of-n OT protocol. To prevent this kind of attack, this paper provides a general framework on how to design a secure OT protocol based on commutative and ciphertext equality test and take RSA as an example to explain how the protocol is processed.