Лучшие интеллектуальные исследованияQurbonov Yorqinbek Avazxonovich2025
Medium-Term Forecasting Of Investment Portfolio Profitability
PAGE NO. - · Medium-Term Forecasting Of Investment Portfolio · Tursunkhodjayeva Shirin
International Journal Of Management And Economics Fundamental · 05 · 987-1007 · 2025
Аннотация
This study explores medium-term forecasting of investment portfolio profitability by analyzing the stock prices of six Uzbek joint-stock companies using time series models. The research compares classical statistical models such as ARIMA with nonlinear models like GARCH and LSTM to determine their accuracy in volatile market conditions. Over 848 ARIMA model combinations were tested, and the most optimal models were selected based on statistical indicators such as AIC, BIC, and significance of parameters. Findings revealed that combining ARIMA with GARCH models improves forecast precision due to the volatility observed in stock returns. The study also highlights that while residuals exhibit autocorrelation and non-normality, the models remain statistically robust for forecasting daily prices from August 2024 to December 2027. The research supports the need for hybrid approaches to better capture the dynamics of financial markets. Keywords: ARIMA, GARCH, Stock Price Forecasting, Time Series Models, Investment Portfolio, Financial Market Volatility, Uzbekistan Stock Market, Forecast Accuracy, Nonlinear Models, Econometric Analysis, ARCH Effect, Neural Networks (LSTM, ANN). used different models to implement this forecast. Introduction: Stock price forecasting has a huge impact However, prioritizing any one model still remains a on the country's economy. After all, the financial complex process. Because the financial market is a non- market plays an important role in the country's linear, highly volatile market, the uncertainty of the economy. Being able to forecast market movements data in it and the shortcomings of forecasting models increases interest in it, thereby contributing to the complicate the forecasting process. In addition, the development of the financial market. Data on the presence of various factors such as the irrational or financial market mainly consists of time series data. rational behavior of investors, their emotional and Therefore, financial market forecasting is carried out psychological state make the movement in the financial based on historical data. Based on the principle that market more dynamic. The fact that stock prices also “history repeats itself” in the financial market, have sharp and unstable fluctuations under the investors and financial analysts forecast stock returns influence of internal and external factors such as based on the current market situation. Choosing the various news and published reports can lead to errors optimal model is important when forecasting the in forecasting. According to Shah, the growth of social return on an investment portfolio, stocks, and the and Internet-based media has had a significant impact financial market in general. Because, accordingly, the on the interaction between public opinion and stock investor determines the entry and exit points of the market dynamics. market, which, based on sound information, helps to make the right decision to invest capital in the financial The following figure shows the main models used in market and get high profits. Different economists have financial market forecasting: (See Figure 4.9) International Journal of Management and Economics Fundamental 108 https://theusajournals.com/index.php/ijmef International Journal of Management and Economics Fundamental (ISSN: 2771-2257) Vaqtli qatorlarni prognozlashda foydalaniladigan modellar Chiziqli modellar Chiziqsiz modellar Statistik Stoxastik Statistik Neytral tarmoqlar ARIMA, VAR, Geometrik brown ANN, CNN, RNN, ARCH, GARCH VEC harakati LSTM Figure 4.9. Models used in time series forecasting 430 by Srivastava found the LSTM model to be the most Autoregressive (linear statistical) models study the suitable model for working with time series data among coefficients that model the relationship between other neutral network models. A number of other several time steps for a target percentage scientists have compared neutral network models with characteristic. One of the popular autoregressive classical statistical models and noted that neutral methods is the autoregressive integrated moving network models are more powerful in many respects. average (ARIMA) model. It was proposed by Kumar and For example, scientists such as Namini and Rhanoui Jain in 2010. ARIMA predicts the future as a linear have shown in their studies that LSTM is superior to combination of historical values and errors, eliminating ARIMA, and Gurushin has proven that even models the trending nature of the variables by implementing that combine statistical and neutral network models differentiation. It is especially effective for short-term (GARCH-ANN, EGRACH-ANN) are less effective than a forecasting. The advantages of these models are their simple ANN model. The fact that stock prices are short-term forecasting efficiency, ease of description, associated with volatility makes it possible to forecast and ability to detect seasonality. However, the inability them using the GARCH model. Since
Доказательный фрагмент
«This study explores medium-term forecasting of investment portfolio profitability by analyzing the stock prices of six Uzbek joint-stock companies using time series models.»
Образец извлечения
Демо-превьюThis study explores medium-term forecasting of investment portfolio profitability by analyzing the stock prices of six Uzbek joint-stock companies using time series models. Полный текст публикации CiteX не хранит — доступ к первоисточнику открывается по DOI согласно лицензии издателя и выбранному плану.
- Цитирований
- 0
- Просмотров
- 0
- Тип
- Журнал
- Страна
- Узбекистан
- Ключевые слова
- ARIMA, GARCH, Stock Price Forecasting, Time Series Models, Investment Portfolio, Financial Market, autoimmune thyroiditis, thyroid nodules, tumors., FNAB, cytology, thyroid gland
Смежные источники
Экономика и инновационные технологииЭгамбердиев Фармонқул Турсунқулович, Ёқубжонова Ҳулкарбону Ёқубовна2018
The American Journal of Applied sciencesShohista Qobiljonovna Yuldasheva, Okhistaxon Khabibjonova2021
Экономика и инновационные технологииКаримов Норбой Ганиевич, Султанов Махмуд Ахмедович2018