Popular Prediction Models Research Articles

PROBABILITY OF DEFAULT, INTEREST MARGIN, AND BANK EFFICIENCY: EMPIRICAL TEST OF MERTON MODEL IN INDONESIAN BANKING

Measurement of bank failure risk is still a challenging research problem. This study is aimed to measure the Indonesia banks probability of bankruptcywith Model Merton which has the better predictive power and is based on a far stronger financial theoretical frameworkcompared to the popular bankruptcy prediction model which is categorized by Sundaresan (2013) as a theoretical model such as Altman Z-score model and Ohlson 0 score more popular. The study also examine the relationship of bank efficiency and market power with its probability of default. The test results demonstrate that bank efficiency significantly affects the dynamics of bank’s default risk.

Edge Popularity Prediction Based on Social-Driven Propagation Dynamics

Caching contents in edge networks can reduce latency and lighten the burden on backhaul links. Since the capacity of cache nodes is limited, accurate content popularity distribution is crucial to the effectual usage of cache capacity. However, existing popularity prediction models stem from big data and, hence, may suffer poor accuracy due to the small population in edge caching. In this letter, we propose a social-driven propagation dynamics-based prediction model, which requires neither training phases nor prior knowledge. Specifically, we first explore social relationships to bridge the gap between small population and prediction accuracy under susceptible-infected-recovery model. Then, a discrete-time markov chain approach is proposed to predict the viewing probability of certain contents from the perspective of individuals. Simulations validate that our proposed model outperforms other solutions significantly, by improving up to 94% in accuracy and 99% less runtime overhead.

Methods of MicroRNA Promoter Prediction and Transcription Factor Mediated Regulatory Network.

MicroRNAs (miRNAs) are short (~22 nucleotides) noncoding RNAs and disseminated throughout the genome, either in the intergenic regions or in the intronic sequences of protein-coding genes. MiRNAs have been proved to play important roles in regulating gene expression. Hence, understanding the transcriptional mechanism of miRNA genes is a very critical step to uncover the whole regulatory network. A number of miRNA promoter prediction models have been proposed in the past decade. This review summarized several most popular miRNA promoter prediction models which used genome sequence features, or other features, for example, histone markers, RNA Pol II binding sites, and nucleosome-free regions, achieved by high-throughput sequencing data. Some databases were described as resources for miRNA promoter information. We then performed comprehensive discussion on prediction and identification of transcription factor mediated microRNA regulatory networks.

A new approach for crude oil price prediction based on stream learning

Crude oil is the world's leading fuel, and its prices have a big impact on the global environment, economy as well as oil exploration and exploitation activities. Oil price forecasts are very useful to industries, governments and individuals. Although many methods have been developed for predicting oil prices, it remains one of the most challenging forecasting problems due to the high volatility of oil prices. In this paper, we propose a novel approach for crude oil price prediction based on a new machine learning paradigm called stream learning. The main advantage of our stream learning approach is that the prediction model can capture the changing pattern of oil prices since the model is continuously updated whenever new oil price data are available, with very small constant overhead. To evaluate the forecasting ability of our stream learning model, we compare it with three other popular oil price prediction models. The experiment results show that our stream learning model achieves the highest accuracy in terms of both mean squared prediction error and directional accuracy ratio over a variety of forecast time horizons.

A Novel Time Series Approach for Predicting the Long-Term Popularity of Online Videos

Predicting the video popularity is an essential part of fast growing online media services. It is beneficial to an array of domains, from targeted advertising, personalized recommendation, to traffic load optimization. However, popularity prediction is a challenge problem due to the uncertainty of information cascade. In this paper, we treat the popularity of online videos as time series over the given periods and propose a novel time series model for popularity prediction. The proposed model is based on the correlation between early and future popularity series. Instead of inferring the precise view counts for a video, this paper focuses on accurately identifying the most popular videos based on the predicted popularity, because it is of the most interest to service providers. Experimental result on real world data have demonstrated that the proposed model outperforms several existing popularity prediction models.

An Early Assessment of Medium Range Monsoon Precipitation Forecasts from the Latest High-Resolution NCEP-GFS (T1534) Model over South Asia

Reliable prediction of the South Asian monsoon rainfall and its variability is crucial for various hydrological applications and early warning systems. The National Centers for Environmental Prediction-Global Forecast System (NCEP-GFS) is one of the popular global deterministic numerical weather prediction models, which is recently upgraded from T574 to T1534. In this paper, medium range monsoon precipitation forecasts from both the T1534 and T574 models are critically evaluated over the South Asia for the peak monsoon months (July and August) of 2015. Although both the versions of GFS model show similar large-scale monsoon rainfall patterns, the dry bias over the northwest India and equatorial Indian Ocean is noticeably improved in day-1 through day-5 forecasts in the new high-resolution T1534 model. The error decomposition analysis shows similar error characteristics in the monsoon rainfall prediction from both the versions of GFS model, in general. However, forecast improvement factor shows 10–30 % improvement in precipitation forecast from the latest T1534 model over most parts of the South Asia. These preliminary analyses suggest that a suitable bias-correction to the GFS model precipitation forecasts will be useful for any specific application.

Analyzing and predicting news popularity on Twitter

Twitter is not only a social network, but also an increasingly important news media. In Twitter, retweeting is the most important information propagation mechanism, and supernodes (news medias) that have many followers are the most important information sources. Therefore, it is important to understand the news retweet propagation from supernodes and predict news popularity quickly at the very first few seconds upon publishing. Such understanding and prediction will benefit many applications such as social media management, advertisement and interaction optimization between news medias and followers. In this paper, we identify the characteristics of news propagation from supernodes from the trace data we crawled from Twitter. Based on the characteristics, we build a news popularity prediction model that can predict the final number of retweets of a news tweet very quickly. Through trace-driven experiments, we then validate our prediction model by comparing our predicted popularity and real popularity, and show its superior performance in comparison with the regression prediction model. From the study, we found that the average interaction frequency between the retweeters and the news source is correlated with news popularity. Also, the negative sentiment of news has some correlations with retweet popularity while the positive sentiment of news does not have such obvious correlation.

Displacement thickness evaluation for semi-empirical airfoil trailing-edge noise prediction model

This study proposes a criterion for evaluating the turbulent boundary layer displacement thickness when predicting airfoil trailing-edge noise with semi-empirical methods. The boundary layer integral parameter is usually employed as the typical turbulence length-scale in the classic NASA-BPM semi-empirical airfoil self-noise prediction model and its variations. Although the semi-empirical noise prediction methods have been, in theory, superseded by more complex and demanding simplified-theoretical methods, they arguably remain the most suitable methods for noise investigation during the preliminary design phase of airfoils and wind turbine blades. The purpose of the criterion discussed is to limit the adverse impact of the uncertainty associated with the scaling parameter into the overall intrinsic quality of the semi-empirical noise prediction method. The criterion may be then employed, along with computational efficiency, to sort out methods for the task of feeding the popular BPM noise prediction model and its variations. As an illustration of the application of the proposed criterion, the performance of CFD-RANS and XFoil codes are examined and compared with experimental data from turbulent, incompressible flow available from the literature in the range $$5.0 \times 10^{5} < \text{Re}_{\text{C}} < 1.5\, \times 10^{6}$$ .

Tracking a tropical cyclone through WRF–ARW simulation and sensitivity of model physics

The Weather Research and Forecasting (WRF) model’s Advanced Research WRF (ARW) dynamic solver is one of the most popular regional numerical weather prediction models being used by operational and research personnel. In this study, we simulate a tropical cyclone to reproduce the track direction and strength of the storm that formed at low latitudes in the West Pacific Ocean. The cyclone is known as “Haiyan” and assessed as category-5 equivalent super typhoon status due to its strong sustained winds and gusts, making it the strongest tropical cyclone in the region. We study the sensitivity of three different model physics options: the microphysics schemes, the planetary boundary layer schemes, and the impact of cumulus parameterization schemes. The realism of the cyclone simulation for different physics options is assessed through the comparison between the model outputs and the best track data, which are taken from the Japan Meteorological Agency. The experimental model simulations are carried out with two different global datasets: the ERA-Interim analysis from the European Centre for Medium Range Weather Forecasts and NCEP GFS forecast data, as initialization and boundary conditions. In addition, wind–pressure relationships are developed for different physics combination runs. Verification results associated with the model physics and boundary condition are discussed in this article. Overall, irrespective of the physics sensitivity, while the WRF simulation performs well in predicting the track propagation of the typhoon, substantial underestimation is seen in the intensity prediction.

A survey on predicting the popularity of web content

Social media platforms have democratized the process of web content creation allowing mere consumers to become creators and distributors of content. But this has also contributed to an explosive growth of information and has intensified the online competition for users attention, since only a small number of items become popular while the rest remain unknown. Understanding what makes one item more popular than another, observing its popularity dynamics, and being able to predict its popularity has thus attracted a lot of interest in the past few years. Predicting the popularity of web content is useful in many areas such as network dimensioning (e.g., caching and replication), online marketing (e.g., recommendation systems and media advertising), or real-world outcome prediction (e.g., economical trends). In this survey, we review the current findings on web content popularity prediction. We describe the different popularity prediction models, present the features that have shown good predictive capabilities, and reveal factors known to influence web content popularity.

Towards Cross-Domain Learning for Social Video Popularity Prediction

Previous research on online media popularity prediction concluded that the rise in popularity of online videos maintains a conventional logarithmic distribution. However, recent studies have shown that a significant portion of online videos exhibit bursty/sudden rise in popularity, which cannot be accounted for by video domain features alone. In this paper, we propose a novel transfer learning framework that utilizes knowledge from social streams (e.g., Twitter) to grasp sudden popularity bursts in online content. We develop a transfer learning algorithm that can learn topics from social streams allowing us to model the social prominence of video content and improve popularity predictions in the video domain. Our transfer learning framework has the ability to scale with incoming stream of tweets, harnessing physical world event information in real-time. Using data comprising of 10.2 million tweets and 3.5 million YouTube videos, we show that social prominence of the video topic (context) is responsible for the sudden rise in its popularity where social trends have a ripple effect as they spread from the Twitter domain to the video domain. We envision that our cross-domain popularity prediction model will be substantially useful for various media applications that could not be previously solved by traditional multimedia techniques alone.

Research on Hybrid Ray-tracing at 2.4 GHz in Man-Made Forests

The shadow of diffraction, which account for the growth of trees based on wireless sensors and automatic acquisition of environmental information, were presented to meet the requirements for a wireless sensor network in a forest. there’s a necessity to avoid the dead zone of signal diffraction when laying wireless sensor in the forest, the integration of SBR and UTD is applied to study the impact of 2.4GHz radio-frequency signal on the path loss characteristics in the forest. Shadow fading is studied by considering random variations of trees height and position. Path loss to subscribers located in a forest are found using refraction and diffraction concepts. This paper achieved the ray location from the receive pint to field point by using back-ray tracing method and computed the response electric field relative to each ray by using UTD. This article presents an overview of popular prediction models and describes electric field algorithms that are based on the authors' experience, to improve their accuracy. Take the poplar planted forest for instance. The measured value and simulated value were compared, finding good consistency between them, which indicates that SBR and UTD can effectively predict the path loss characteristics in the forest. DOI: http://dx.doi.org/10.11591/telkomnika.v11i7.2833 Full Text: PDF

Re-evaluation of building cooling load prediction models for use in humid subtropical area

For buildings in subtropical area with negligible heating load, prediction of short term building cooling load is of critical importance to achieve the energy saving target. However, due to the limitation of simplified models and the difficulty in predicting weather and internal thermal load and mass, accurate prediction of cooling load is very challenging. Realizing that building cooling load is uncertain by nature, this paper re-evaluates four popular prediction models in terms of: (1) load prediction accuracy, (2) adaptability to room temperature set point and (3) ability to predict a load probability distribution curve that is consistent for various scenarios (different internal and external thermal mass). The four models are Autoregressive Moving Average with Exogenous inputs (ARMAX) model, Multiple Linear Regression (MLR) model, Artificial Neural Network (ANN) model and Resistor–Capacitor (RC) network (a simplified physical model). The results show that the MLR model and the ARMAX model are superior in prediction accuracy and precision; the RC network model is superior in adaptability to control set points. Since none of the models give prediction errors that follow normal distribution, further development of load prediction model is urgently necessary.

Using Negative Binomial Regression Analysis to Predict Software Faults: A Study of Apache Ant

Negative binomial regression has been proposed as an approach to predicting fault-prone software modules. However, little work has been reported to study the strength, weakness, and applicability of this method. In this paper, we present a deep study to investigate the effectiveness of using negative binomial regression to predict fault-prone software modules under two different conditions, self- assessment and forward assessment. The performance of negative binomial regression model is also compared with another popular fault prediction model—binary logistic regression method. The study is performed on six versions of an open-source objected-oriented project, Apache Ant. The study shows (1) the performance of forward assessment is better than or at least as same as the performance of self-assessment; (2) in predicting fault-prone modules, negative binomial regression model could not outperform binary logistic regression model; and (3) negative binomial regression is effective in predicting multiple errors in one module.

Fuzzy-C-Mean Based Radial Basis Function Network Application in Machinery Noise Prediction

Advanced mechanized in opencast mines in now-a-days expected to intensify more noise problems in working environment. Prolonged exposure of miners to the high levels of noise can cause noise induced hearing loss besides several non-auditory health effects. To maintain the good working environment in mines, appropriate noise survey of machineries should be conducted. Hence in order to improve the environmental condition in working place, it is needed to develop appropriate noise prediction model for finding out the accurate status of noise levels from various surface mining machineries. The measured sound pressure level (SPL) of equipments is not accurate due to instrumental error, attenuation, geometrical aberration, atmospheric attenuation etc. Some of the popular noise prediction models e.g. ISO: 9613-2, ENM, CONCAWE have been applied in mining and allied industries. In this paper, an advanced radial basis neural network (RBFN) has been proposed. Two types of RBFN architectures: Generalized Radial Basis Function Network (GRBFN) and Fuzzy-C-Mean based Radial Basis Function Network (FCMRBFN) were used to predict the machinery noise in a large opencast bauxite mine. The proposed models were designed with ISO: 9613-2 noise prediction guidelines considering 1/1 octave band. From the present investigation, it can be concluded that, the output of FCMRBFN system based noise prediction models closely matches with the ISO: 9613-2 model output.

Country risk forecasting for major oil exporting countries: A decomposition hybrid approach

From the perspective of energy security, this paper focuses on country risk forecasting for major oil exporting countries. Due to the two main characteristics of country risk of oil exporting countries, i.e. the complexity and the mutability, this study proposes a decomposition hybrid approach (DHA) for predicting country risk of oil exporters, based on the principle of “decomposition and ensemble” and the strategy of “divide and conquer”. In DHA, effective decomposition methods, such as ensemble empirical mode decomposition (EEMD), are specially introduced to decompose oil exporter’s country risk into a series of relatively easily forecasting components; powerful prediction tools, such as least squares support vector regression (LSSVR), are then implemented to predict all extracted components; and finally these predicted results are fused into an ensemble for the original data via ensemble approaches, such as LSSVR model or simple addition (ADD) approach. Experimental results, with ten major oil exporters as study samples, demonstrate that DHA with decomposition process can be statistically proved to be much stronger and more robust than other popular prediction models.

A new approach for manufacturing forecast problems with insufficient data: the case of TFT–LCDs

Manufacturing forecast problems have been widely discussed in recent years, where more accurate predictions could reduce the overall manufacturing costs. This study uses the case of ensuring the heights of thin film transistor---liquid crystal display photo-spacers. It is a small sample size prediction problem, because the data available for analysis is limited on the manufacturing lines. A new approach is developed to deal with this problem, which involves three steps. The first step is using K-means clustering to separate data into K clusters, while the second step is to compute the possibility through the fuzzy membership function in each cluster for attribute extension. The last step is to put the data with new generate attributes into a backpropagation neural network (BPNN) machine learning algorithm. Two performance evaluation methods, cross-validation and data specification testing, are selected to compare the proposed method with three popular prediction models: linear regression, support vector machine for regression (SVR), and BPNN. The results show that the proposed method outperforms the others with regard to the total errors, mean square error, and standard deviation.

A soft computing system for opencast mining machineries noise prediction

In this paper, soft computing based system models were applied to predict opencast mining machineries noise. Noise is often regarded as a nuisance rather than as an occupational hazard in an opencast mining environment. Prolonged exposure to noise over a period of years generally causes permanent damage to the auditory nerve and/or its sensory components. To maintain the good working environment in mines, appropriate noise survey of machineries should be conducted. The measured sound pressure levels (SPL) for the equipments by sound measuring devices are considered inaccurate due to instrumental error, attenuation due to geometrical aberration, atmospheric attenuation etc. Some of the popular noise prediction models e.g. ISO-9613-2, CONCAWE, VDI and ENM have been applied in mining and allied industries to predict the machineries noise by considering all the attenuation factors. Mamdani, Takagi Sugeno Kang (T-S-K) fuzzy inference system and Adaptive Network based Fuzzy inference System (ANFIS) were used to predict the machinery noise in opencast mines. From the present investigations, it was observed that the ANFIS model gave better noise prediction than the Mamdani and TSK fuzzy model

Application of Functional Link Artificial Neural Network for Prediction of Machinery Noise in Opencast Mines

Functional link-based neural network models were applied to predict opencast mining machineries noise. The paper analyzes the prediction capabilities of functional link neural network based noise prediction models vis-à-vis existing statistical models. In order to find the actual noise status in opencast mines, some of the popular noise prediction models, for example, ISO-9613-2, CONCAWE, VDI, and ENM, have been applied in mining and allied industries to predict the machineries noise by considering various attenuation factors. Functional link artificial neural network (FLANN), polynomial perceptron network (PPN), and Legendre neural network (LeNN) were used to predict the machinery noise in opencast mines. The case study is based on data collected from an opencast coal mine of Orissa, India. From the present investigations, it could be concluded that the FLANN model give better noise prediction than the PPN and LeNN model.

Machinery Noise Prediction in Opencast Mines Using Concawe Model: A Case Study

Noise is often regarded as a nuisance rather than as an occupational hazard in an opencast mining environment. Prolonged exposure to noise over a period of years generally causes permanent damage to the auditory nerve and/or its sensory components. To maintain the good working environment in mines, appropriate noise survey of machineries should be conducted. The measured sound pressure levels (SPL) of equipment are not accurate due to instrumental error, attenuation due to geometrical aberration, atmospheric attenuation etc. Some of the popular noise prediction models e.g. CONCAWE, VDI and ENM have been applied in mining and allied industries to predict the machineries noise by considering all the attenuation factors. In this paper, authors have predicted machineries noise in an opencast mine using CONCAWE model.