درخت حوزه‌های تخصصی

This study focuses on providing an intelligent credit risk management system of the bank in the presence of the macroeconomic indicators using a combined methodology of econometrics and artificial intelligence. In addition to the use of scientific documents and reports, the panel data related to the annual reports and datasets of stock exchange banks are analyzed by using the MATLAB programming environment. One of the most important results of the this paper is that the proposed approach has been based on the calculations made with the GARCH economic model in which the input values of the component "Inflation rate factor (A4)” have a weight of 0.943734 (equivalent to the membership function "High H"); the component "rate factor Bank deposit (B4)” has a weight of 0.959346 (equivalent to the "High H" membership function); the component “Unemployment rate factor (A3)” has a weight of 0.990343 (equivalent to the "High H" membership function); the component "Exchange Rate Factor (B2)" has a weight of 0.990413 (equivalent to the membership function "High H"); And the component "GDP growth rate factor (A1)” has a weight of 0.959256 (equivalent to the membership function of "high H"); This means that, 5.46 is within a range of 6, i.e. the target variable is exactly in the 91st position (the fifth level of the system output is excellent).

Due to the rapid advancements in computer technology, researchers are attracted to solving challenging problems in many different fields. The price of rainbow options is an interesting problem in financial fields and risk management. When there is no closed-form solution to some options, numerical methods must be used. Choosing a suitable numerical method involves the most appropriate combination of criteria for speed, accuracy, simplicity and generality. Monte Carlo simulation methods and traditional numerical methods have expensive repetitive computations and unrealistic assumptions on the model. Deep learning provides an effective and efficient method for options pricing. In this paper, the closed-form formula or Monte-Carlo simulation are used to generate data in European and Asian rainbow option prices for the deep learning model. The results confirm that the deep learning model can price the rainbow options more accurately with less computation time than Monte-Carlo simulation.

The worldwide Covid-19 epidemic while affecting numerous places, has had a profound effect on virtual advertising and advertising and, globally, in the provinces and at the neighborhood level. except, this effect for the most element become positive, in contrast to what has seen in exclusive sectors which include economy, human sources, etc., whilst contamination reasons a variety of incapacity amongst clients and advertisers alike, in phrases of welfare, social work, inflation, business, and many others., the equal shifted conduct goes as a long way as running. , investing strength, getting into self-schooling, adopting new programs from the internet, expanding social and hygiene concerns, retaining distance strategies from complete regions, internet-based media willpower, get right of entry to online sources, etc., and this has greatly impacted the display and endorsed efforts. The moral movement has moved past the PC and digital international, which places open doors for advertisers and products to connect with clients more efficiently than ever before. With the arrival of expanded online media and the call for pc-generated content material, the evolved Media have given advertisers a part of the monetary freedom. At the equal time, this has, in turn, enabling advertisers to be extra proactive and to engage with the public at the same time as appearing excessive excellent demonstration programs. The purpose of this study is to explore, investigate, and recognize the effect of coronavirus on the digital market and businesses.

Human Identification has been widely implemented to enhance the efficiency of surveillance systems, however, systems based on common CCTV (closed-circuit television) cameras are mostly incompatible with the advanced identification algorithms which aim to extract the facial features or speech of an individual for identification. Gait (i.e., an individual’s unique walking pattern/style) is a leading exponent when compared to first-generation biometric modalities as it is unobtrusive (i.e., it requires no contact with the individual), hence proving gait to be an optimal solution to human identification at a distance. This paper proposes an automatic identification system that analyzes gait to identify humans at a distance and predicts the strength of the match (i.e., probability of the match being positive) between two gait profiles. This is achieved by incorporating computer vision, digital image processing, vectorization, artificial intelligence, and multi-threading. The proposed model extracts gait profiles (from low-resolution camera feeds) by breaking down the complete gait cycle into four quarter-cycles using the variations in the width of the region-of-interest and then saves the gait profile in the form of four distinct projections (i.e., vectors) of length 20 units each, thus, summing up to 80 features for each individual’s gait profile. The focus of this study revolved around the speed-accuracy tradeoff of the proposed model where, with a limited dataset and training, the model runs at a speed of 30Hz and yields 85% accurate results on average. A Receiver Operating Characteristic Curve (ROC) is obtained for comparison of the proposed model with other machine learning models to better understand the efficiency of the system