One of the key capabilities of competitive online stores is the effective prediction of customer buying as much as possible to apply customer service strategies to convert users to buyers and to increase sales rates. Data mining and artificial intelligence techniques ar More
One of the key capabilities of competitive online stores is the effective prediction of customer buying as much as possible to apply customer service strategies to convert users to buyers and to increase sales rates. Data mining and artificial intelligence techniques are successful in categorizing and forecasting. Work has been proven in timely systems, such as e-commerce sites. In this paper, we propose a non-post-error neural network model with the aim of predicting purchases at user active stages in an online store. The training and evaluation of the neural network was performed using a set of revised sessions from server logs. The accuracy and retrieval power of the proposed neural network is 8999.79% and 89.696%, which indicates the high ability of this network (about 90%) in predicting the purchase
Manuscript profile
Risk parity is one of the stock portfolio selection models that has received much attention after the American financial crisis in 2008. The philosophy of this model is to allocate the risk of the portfolio to the same extent among its constituent assets. Conditional va More
Risk parity is one of the stock portfolio selection models that has received much attention after the American financial crisis in 2008. The philosophy of this model is to allocate the risk of the portfolio to the same extent among its constituent assets. Conditional value at risk is one of the popular and common measures of risk measurement in finance, which measures the mathematical expectation of loss of a stock portfolio for values beyond a threshold value and at a known confidence level and time horizon. The aim of the current research is to design and optimize the performance of the risk parity stock portfolio model with the criterion of conditional risk value. There are different approaches in modeling optimal portfolio selection that use different criteria and methods to calculate and estimate returns and risks. Various criteria have been proposed to measure risk in finance, each of which has its own advantages and disadvantages. One of the criteria that has been introduced with the aim of reducing the disadvantages of the common and popular measure of value at risk is the conditional value at risk or expected drop, which is used as a measure of risk in the present study. Conditional value at risk measures the average loss of the portfolio for cases where the amount of loss exceeds value at risk
Manuscript profile
