Asset volatility forecasting:The optimal decay parameter in the EWMA model

Araneda, Axel A.

doi:10.48550/arxiv.2105.14382

Cited by 3 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…EGARCH-M was used by Harvey and Lange [17] to forecast and examine the relationship between volatility and returns. By using the ideal decay parameters in the EWMA model, Araneda projected asset volatility [18]. Reconstructing weekly and monthly HAR components for projections of the global stock market was done by Liang and his colleagues using the EWMA approach [19].…”

Section: Literature Reviewmentioning

confidence: 99%

The performance and error analysis of LSTM model combined with various GARCH models in stock forecasting

Chen¹,

Yang²,

Zhu³

et al. 2023

Second International Conference on Green Communication, Network, and Internet of Things (CNIoT 2022)

View full text Add to dashboard Cite

Volatility is a measure of the asset return rate's estimated level of uncertainty and may be used to assess the riskiness of financial assets. We use the market capitalization of 200 stocks representing Korea as the primary analytical aim and evaluate the accuracy between them by analyzing the impacts of different hybrid models' hybrid neural networks, which are based on the returns of the KOSPI 200 stock index. By measuring the effectiveness of these models using four dissimilarity measures, we contrasted the performance of hybrid models that combine a single neural network and a single GARCH type model with that of hybrid neural networks that combine multiple GARCH models (MAE, MSE, HMAE, and HMSE). They are applied to anticipate the KOSPI 200 index data's actual volatility. Among these, hybrid neural networks that integrate more than one GARCH-type model have much better forecasting performance than neural network models that mix two or more or more GARCH-type models. GW-LSTM makes the least accurate forecast. We note that the hybrid model combining the three GARCH models shows a minor increase in predicting ability based on merging two and three models.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

The performance and error analysis of LSTM model combined with various GARCH models in stock forecasting

Chen¹,

Yang²,

Zhu³

et al. 2023

Second International Conference on Green Communication, Network, and Internet of Things (CNIoT 2022)

View full text Add to dashboard Cite

show abstract

“…These include but are not limited to the use of statistical methods, for example, linear modelling, machine learning and weighted moving averages (Pichler et al, 2020;Tredennick et al, 2021). Participants of the financial markets make use of algorithms to predict how the markets will respond in the future based on known data (Granger & Poon, 2003), here weighted moving averages are reliably used to predict the level of market volatility (Araneda, 2021;Broll & Förster, 2022;Granger & Poon, 2003;Gurrola-Perez, 2021). Ecological studies have historically used weighted moving averages to predict behaviours associated with foraging (Devenport & Devenport, 1994) and budget allocation to prey selection (McNamara & Houston, 1987), and recently in mussel behaviour prediction for online monitoring of oil pollution (Guterres et al, 2020), with application in fish behavioural studies limited (Brownscombe et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Detecting changes in fish behaviour in real time to alert managers to thresholds of potential concern

Burnett,

Süßle,

Saayman

et al. 2023

River Research & Apps

View full text Add to dashboard Cite

Fish behaviour is one biological organisational level regularly used to assess the state of freshwater ecosystems and can be monitored using fish telemetry methods. The development of activity sensors incorporated into fish telemetered tags allows for non‐spatial movement to be detected and is increasingly used to understand the energy budgets and response and fine‐scale behaviour of fishes. In addition, detecting tagged fish remotely and in real time highlights the need to process fish activity data in near real time to make it relevant to managers in the water resource sector. Our study on Labeobarbus natalensis, a cyprinid, in the uMngeni River in KwaZulu‐Natal, South Africa, adapted and then tested the exponentially weighted moving average (EWMA), as developed for financial predictive modelling, using activity data from fish. To determine changes in behaviour, we compared the EWMA‐predicted fish behaviour against the present fish behaviour. We showed that the EWMA could adequately detect changes in behaviour on both individual and population levels. Changes in behaviour are potentially indicative of a change in environmental conditions and thus were developed into management alerts. We conducted further analyses using generalised additive mixed models (GAMM) to determine the relationship between fish activity and the environmental data collected. The GAMMs helped determine the potential drivers for changes in behaviour where the EWMA could detect these in real time. Detecting changes in behaviour in real time as a result of environmental variables can identify thresholds of potential concern influencing management decisions and allow managers to respond, contributing to improving effective freshwater management.

show abstract

“…EWMA model is a model used to predict the volatility of stock based on historical data. Axel had found the optimal decay parameter for this model by comparing the result of different parameter values [7]. Clustering algorithms have been applied to construct portfolio formation by researchers.…”

Section: Introductionmentioning

confidence: 99%

The Study of Using Machine Learning Algorithms to Construct Portfolio Formation

Chen¹

2022

Proceedings of the 2022 7th International Conference on Financial Innovation and Economic Development (ICFIED 2022)

View full text Add to dashboard Cite

The earning of the investors in the stock market is related to their investment choice and the behavior of the stocks. The key to investors making a more intelligent investment decision is to predict the price and volatility of the stocks accurately. In addition, building a portfolio formation is also an effective way to reduce investment risk. However, the stock price is beyond the predictive ability of any individual, and the portfolio formations are hard to build due to the stock market volatiles incessantly. In such a condition, this project attempts to propose a methodology for designing portfolio formations by using machine learning methods. The ultimate aim of this project is to predict the profit and volatility of stocks in the American stock market and use these predictions to construct portfolio formations. In this paper, the Support Vector Machine (SVM), Light Gradient Boosting Machine (LGBM), and Long Short-Term Memory model (LSTM) are used to predict the tendency of stocks. The experiment result shows that the LGBM model has the best performance on stocks price prediction. Based on the prediction of price, investing profit is easy to predict. The financial model called exponential weighted moving average (EWMA) is used to calculate the volatility of the stocks. After getting the prediction of profit and volatility, using the spectral clustering algorithm can get the portfolio formation. The result shows that the portfolio formation given by the proposed model has high profit and low volatility.

show abstract

Asset volatility forecasting:The optimal decay parameter in the EWMA model

Cited by 3 publications

References 9 publications

The performance and error analysis of LSTM model combined with various GARCH models in stock forecasting

The performance and error analysis of LSTM model combined with various GARCH models in stock forecasting

Detecting changes in fish behaviour in real time to alert managers to thresholds of potential concern

The Study of Using Machine Learning Algorithms to Construct Portfolio Formation

Contact Info

Product

Resources

About