We aim to detect outliers in the daily stock price indices from Saudi Arabia exchange (Tadawul) with 2026 observations October 2011 December 2019 provided by Authority for Statistics and Central Bank. apply Multi-Layer Perceptron (MLP) algorithm detecting returns. select inflation rate (Inflation), oil (Loil), repo (Repo) as input variables MLP architecture. The performance of is evaluated using standard metrics binary classification, namely false positive (FP rate), negative (FN F-measure,...

Bangladesh remains one of the most vulnerable countries in world to effects climate change. Given reliance a large segment population on agricultural sector for both their livelihoods as well national food security, change adaptation is crucial continued security and economic growth. Using household data from lowland rice farmers selected haor areas Sylhet, current work presents an analysis determinants behind implementation different strategies by farmers. The first objective this study was...

Many researchers documented that the stock market data are nonstationary and nonlinear time series data. In this study, we use EMD-HW bagging method for forecasting. The is based on empirical mode decomposition (EMD), moving block bootstrap Holt-Winter. of six countries used to compare method. This comparison five forecasting error measurements. shows results more accurate than fourteen selected methods.

This study employs Markov-Switching Regression (MS-Regression) to model four macroeconomic indicators—US GDP, CPI, interest rate, and unemployment rate—to identify economic crisis cycles, while all indicators provide some level of insight into these the rate offers closest alignment with actual patterns cycles. Based on regime identification derived from we delineate time series for expansion recession periods. Subsequently, apply Quantile Vector Autoregression (Quantile-VAR) analyze three...

Despite the introduction of several adjustments, mitigating data anomalies in financial datasets has proven challenging, particularly context cryptocurrencies with extreme values and increased volatility. The progress properly addressing these prior to testing remains restricted, highlighting unique complex nature this domain. Thus, paper we propose a hybrid approach called Win-IS strategy. It is meant address influence outliers tail subsequently identify breaks, trend breaks...

Abstract The S&P 500 is a bellwether and leading indicator for the economy as well default vehicle passive investors who want exposure to U.S. via index funds. Since 1957, has performed amazingly, outpacing other asset classes such bonds or commodities. This study seeks develop an appropriate ARIMA model that best fit monthly stock price of period 17 years, 2001–2017, thus make short-term forecast in way give overview help investor portfolio manager decision making. EViews software was...

This study explores the impact of nanofillers on wear and frictional characteristics Cellulosic fibre-reinforced composites. With increasing demand for lightweight durable materials in various industries, understanding effects composite performance is crucial. In this research, pin-on-disc trials were conducted under applied loads ranging from 80 N to 140 N, maintaining a constant 50% fibre volume fraction, sliding distance 3000 m, velocity 1 m/s. The incorporation 5 phr graphite powder was...

Turbidite-associated black shale of the Semanggol Formation is extensively distributed in northwestern part Western Belt, Peninsular Malaysia. The occurs as a dark grey to and thick medium-bedded deposit. It represents distal submarine fan system (outer-fan) overlying interbedded sandstone facies mid-fan conglomeratic pebbly inner-fan. Field observations its widespread occurrence have resulted being considered potential analog for source rock offshore present study includes detailed...

This study aims to model and enhance the forecasting accuracy of Saudi Arabia stock exchange (Tadawul) data patterns using daily price indices with 2026 observations from October 2011 December 2019. employs a nonlinear spectral maximum overlapping discrete wavelet transform (MODWT) five mathematical functions, namely, Haar, Daubechies (Db), Least Square (LA-8), Best localization (BL14), Coiflet (C6) in conjunction adaptive network-based fuzzy inference system (ANFIS). We have selected oil...

This study presents an outcome of pursuing better and effective forecasting methods. The primarily focused on the use divide-and-conquer strategy with Empirical Mode Decomposition or briefly EMD algorithm. We used two different statistical methods to forecast. One is for high-frequency components another low-frequency components. With methods, ARIMA (Autoregressive Integrated Moving Average) EWMA (Exponentially Weighted Average), we investigated possible potential hybrid methods:...

After the East Asian crisis in 1997, issue of whether stock prices and exchange rates are related or not have received much attention. This is due to realization that during countries affected saw turmoil both their currencies markets. paper studies non-linear interactions between price rate Malaysia using a two regimes multivariate Markov switching vector autoregression (MS-VAR) model with regime shifts mean variance. In study, Kuala Lumpur Composite Index (KLCI) ringgit against four other...

In this study, an elastic net (EN) regression model based on the empirical mode decomposition (EMD) algorithm is used in two applications, namely, numerical experiment and actual time series data. EMD to analyze a nonstationary nonlinear signal dataset, which includes set of orthogonal intrinsic functions (IMFs) residual components. EN select most significant predictor variables influencing response can address multicollinearity problem between variables. The main objective study apply...

This empirical research aims to modeling and improving the forecasting accuracy of volatility pattern by employing Saudi Arabia stock market (Tadawul)by studying daily closed price index data from October 2011 December 2019 with a number observations being 2048. In order achieve significant results, this study employs many mathematical functions which are non-linear spectral model Maximum overlapping Discrete Wavelet Transform (MODWT) based on best localized function (Bl14), autoregressive...

In quantile regression models, numerous penalization methods have been developed to deal with ordinary least-squares method problems. Such are ridge penalized regression, lasso and elastic net which used for variable selection regularization deals the multicollinearity problem when it exists between predictor variables. However, variables of interest often represented through time series processes, in such data non-stationary non-linear, leads poor accuracy resultant models hence results...

Abstract Many researchers documented that if stock markets' returns series are significantly skewed, linear-GARCH (1,1) grossly underestimates the forecast values of returns. However, this study showed linear Maximal Overlap Discreet Wavelet Transform MODWT-GARCH actually gives an accurate value The used daily four African countries' market indices for period January 2, 2000, to December 31, 2014. Transform-GARCH model and Transform-EGARCH exhaustively compared. results show although both...

Elastic net (ELNET) regression is a hybrid statistical technique used for regularizing and selecting necessary predictor variables that have strong effect on the response variable deal with multicollinearity problem when it exists between variables. The empirical mode decomposition (EMD) algorithm to decompose nonstationary nonlinear dataset into finite set of orthogonal intrinsic function components one residual component. This study mainly aims apply proposed ELNET-EMD method determine...

<span lang="EN-US">A dataset containing 1924 observations used in this study to evaluate the effect of 435 different independent variables on one dependent variable. Big data has some issues such as irrelevant and outliers. Therefore, focused analysing comparing impact three variable selection based machine learning techniques, including random forest (RF), support vector machines (SVM), Boosting. Further, M robust regression was applied address outliers using M–bi square, M–Hampel,...