arXiv subjects

Jaewoo Kang

Publications and source records attributed to Jaewoo Kang.

112 records · Page 7Linked to original sources

arXiv2019

Global Stock Market Prediction Based on Stock Chart Images Using Deep Q-Network

We applied Deep Q-Network with a Convolutional Neural Network function approximator, which takes stock chart images as input, for making global stock market predictions. Our model not only yields profit in the stock market of the country where it was trained but generally yields profit in global stock markets. We trained our model only in the US market and tested it in 31 different countries over 12 years. The portfolios constructed based on our model's output generally yield about 0.1 to 1.0 percent return per transaction prior to transaction costs in 31 countries. The results show that there are some patterns on stock chart image, that tend to predict the same future stock price movements across global stock markets. Moreover, the results show that future stock prices can be predicted even if the training and testing procedures are done in different countries. Training procedure could be done in relatively large and liquid markets (e.g., USA) and tested in small markets. This result demonstrates that artificial intelligence based stock price forecasting models can be used in relatively small markets (emerging countries) even though they do not have a sufficient amount of data for training.

q-fin.GN↗

arXiv2018

Typeface Completion with Generative Adversarial Networks

The mood of a text and the intention of the writer can be reflected in the typeface. However, in designing a typeface, it is difficult to keep the style of various characters consistent, especially for languages with lots of morphological variations such as Chinese. In this paper, we propose a Typeface Completion Network (TCN) which takes one character as an input, and automatically completes the entire set of characters in the same style as the input characters. Unlike existing models proposed for image-to-image translation, TCN embeds a character image into two separate vectors representing typeface and content. Combined with a reconstruction loss from the latent space, and with other various losses, TCN overcomes the inherent difficulty in designing a typeface. Also, compared to previous image-to-image translation models, TCN generates high quality character images of the same typeface with a much smaller number of model parameters. We validate our proposed model on the Chinese and English character datasets, which is paired data, and the CelebA dataset, which is unpaired data. In these datasets, TCN outperforms recently proposed state-of-the-art models for image-to-image translation. The source code of our model is available at https://github.com/yongqyu/TCN.

cs.CV↗

arXiv2018

Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering

Recently, open-domain question answering (QA) has been combined with machine comprehension models to find answers in a large knowledge source. As open-domain QA requires retrieving relevant documents from text corpora to answer questions, its performance largely depends on the performance of document retrievers. However, since traditional information retrieval systems are not effective in obtaining documents with a high probability of containing answers, they lower the performance of QA systems. Simply extracting more documents increases the number of irrelevant documents, which also degrades the performance of QA systems. In this paper, we introduce Paragraph Ranker which ranks paragraphs of retrieved documents for a higher answer recall with less noise. We show that ranking paragraphs and aggregating answers using Paragraph Ranker improves performance of open-domain QA pipeline on the four open-domain QA datasets by 7.8% on average.

cs.CL↗

arXiv2009

Adaptive BLASTing through the Sequence Dataspace: Theories on Protein Sequence Embedding

We theorize that phylogenetic profiles provide a quantitative method that can relate the structural and functional properties of proteins, as well as their evolutionary relationships. A key feature of phylogenetic profiles is the interoperable data format (e.g. alignment information, physiochemical information, genomic information, etc). Indeed, we have previously demonstrated Position Specific Scoring Matrices (PSSMs) are an informative M-dimension which can be scored from quantitative measure of embedded or unmodified sequence alignments. Moreover, the information obtained from these alignments is informative, even in the twilight zone of sequence similarity (<25% identity)(1-5). Although powerful, our previous embedding strategy suffered from contaminating alignments(embedded AND unmodified) and computational expense. Herein, we describe the logic and algorithmic process for a heuristic embedding strategy (Adaptive GDDA-BLAST, Ada-BLAST). Ada-BLAST on average up to ~19-fold faster and has similar sensitivity to our previous method. Further, we provide data demonstrating the benefits of embedded alignment measurements for isolating secondary structural elements and the classifying transmembrane-domain structure/function. We theorize that sequence-embedding is one of multiple ways that low-identity alignments can be measured and incorporated into high-performance PSSM-based phylogenetic profiles.

q-bio.QM↗