Search

Your search keyword '"Kim, Jeonghun"' showing total 1,000 results
Start Over Author "Kim, Jeonghun"
1,000 results on '"Kim, Jeonghun"'

2. Index Tracking Via Learning to Predict Market Sensitivities

Author

Hong, Yoonsik, Kim, Yanghoon, Kim, Jeonghun, Choi, Yongmin, Kacprzyk, Janusz, Series Editor, Gomide, Fernando, Advisory Editor, Kaynak, Okyay, Advisory Editor, Liu, Derong, Advisory Editor, Pedrycz, Witold, Advisory Editor, Polycarpou, Marios M., Advisory Editor, Rudas, Imre J., Advisory Editor, Wang, Jun, Advisory Editor, and Arai, Kohei, editor

Published
2024
Full Text
View/download PDF

3. Index Tracking via Learning to Predict Market Sensitivities

Author

Hong, Yoonsik, Kim, Yanghoon, Kim, Jeonghun, and Choi, Yongmin

Subjects
Quantitative Finance - Portfolio Management, Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

Index funds are substantially preferred by investors nowadays, and market sensitivities are instrumental in managing index funds. An index fund is a mutual fund aiming to track the returns of a predefined market index (e.g., the S&P 500). A basic strategy to manage an index fund is replicating the index's constituents and weights identically, which is, however, cost-ineffective and impractical. To address this issue, it is required to replicate the index partially with accurately predicted market sensitivities. Accordingly, we propose a novel partial-replication method via learning to predict market sensitivities. We first examine deep-learning models to predict market sensitivities in a supervised manner with our data-processing methods. Then, we propose a partial-index-tracking optimization model controlling the net predicted market sensitivities of the portfolios and index to be the same. These processes' efficacy is corroborated by our experiments on the Korea Stock Price Index 200. Our experiments show a significant reduction of the prediction errors compared with historical estimations and competitive tracking errors of replicating the index utilizing fewer than half of the entire constituents. Therefore, we show that applying deep learning to predict market sensitivities is promising and that our portfolio construction methods are practically effective. Additionally, to our knowledge, this is the first study addressing market sensitivities focused on deep learning.

Published
2022

46. Recent developments of polymer-based encapsulants and backsheets for stable and high-performance silicon photovoltaic modules: materials nanoarchitectonics and mechanisms.

Author

Kim, Donggyun, Lim, Hyunsoo, Kim, Sung Hyun, Lee, Kang No, You, Jungmok, Ryu, Du Yeol, and Kim, Jeonghun

Abstract

Photovoltaic (PV) technology enables the conversion of solar energy into electricity. Si-based PV modules, which currently represent more than 90% of the global PV market, are expected to be in high demand in the future. To increase the efficiency of Si-based PV modules, it is important to improve not only the manufacturing technology and solar cell architecture but also the materials needed to produce the modules. Encapsulants and backsheets, which are used to ensure the long-term lifespan and stability of solar cells, play an equally important role in PV modules as solar cells. Research is being conducted on polymers used in encapsulants and backsheets to increase cell efficiency by using additives or composites with various materials. This article reviews the recent developments of materials and additives for polymer-based encapsulants and backsheets in Si-based PV modules. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

47. An Efficient Checkpoint Strategy for Federated Learning on Heterogeneous Fault-Prone Nodes.

Author

Kim, Jeonghun and Lee, Sunggu

Subjects
FEDERATED learning, ARTIFICIAL neural networks, LEARNING strategies, MACHINE learning, DEEP learning, COMPUTER systems
Abstract

Federated learning (FL) is a distributed machine learning method in which client nodes train deep neural network models locally using their own training data and then send that trained model to a server, which then aggregates all of the trained models into a globally trained model. This protects personal information while enabling machine learning with vast amounts of data through parallel learning. Nodes that train local models are typically mobile or edge devices from which data can be easily obtained. These devices typically run on batteries and use wireless communication, which limits their power, making their computing performance and reliability significantly lower than that of high-performance computing servers. Therefore, training takes a long time, and if something goes wrong, the client may have to start training again from the beginning. If this happens frequently, the training of the global model may slow down and the final performance may deteriorate. In a general computing system, a checkpointing method can be used to solve this problem, but applying an existing checkpointing method to FL may result in excessive overheads. This paper proposes a new FL method for situations with many fault-prone nodes that efficiently utilizes checkpoints. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results