Forward robust portfolio selection: The binomial case

We introduce a new approach for optimal portfolio choice under model ambiguity by incorporating predictable forward preferences in the framework of Angoshtari et al.[2].The investor reassesses and revises the model ambiguity set incrementally in time while,also,updating his risk preferences forward in time.This dynamic alignment of preferences and ambiguity updating results in time-consistent policies and provides a richer,more accurate learning setting.For each investment period,the investor solves a worst-case portfolio optimization over possible market models,which are represented via a Wasserstein neighborhood centered at a binomial distribution.Duality methods from Gao and Kleywegt[10];Blanchet and Murthy[8]are used to solve the optimization problem over a suitable set of measures,yielding an explicit optimal portfolio in the linear case.We analyze the case of linear and quadratic utilities,and provide numerical results.

Modified Adhoc On-Demand Distance Vector for Trust Evaluation And Attack Detection

Recently,Wireless Sensor Network(WSN)becomes most potential technologies for providing improved services to several data gathering and track-ing applications.Because of the wireless medium,multi-hop communication,absence of physical protectivity,and accumulated traffic,WSN is highly vulner-able to security concerns.Therefore,this study explores a specific type of DoS attack identified as a selective forwarding attack where the misbehaving node in the network drops packet on a selective basis.It is challenging to determine if packet loss is caused by a collision in the medium access path,poor channel quality,or a selective forwarding assault.Identifying misbehaving nodes at the earliest opportunity is an acceptable solution for performing secure routing in such networks.As a result,in this study effort,we present a unique Modified Ad Hoc On-Demand Distance Vector(AODV)Routing protocol depending upon the One time password(OTP)method that employs the RSA algorithm.Finally,a trust evaluation process determines which approach is the most optimal.Accord-ing to the simulationfindings of the suggested routing protocol and comparison with existing routing protocols provided in this article,the proposed work is both efficient and cost-effective.

Framework Development Using Data Mining Techniques to Predict Mortality Risk during Pandemic

The corona virus, which causes the respiratory infection Covid-19, was first detected in late 2019. It then spread quickly across the globe in the first months of 2020, reaching more than 15 million confirmed cases by the second half of July. This global impact of the novel coronavirus (COVID-19) requires accurate forecasting about the spread of confirmed cases as well as continuation of analysis of the number of deaths and recoveries. Forecasting requires a huge amount of data. At the same time, forecasts are highly influenced by the reliability of the data, vested interests, and what variables are being predicted. Again, human behavior plays an important role in efficiently controling the spread of novel coronavirus. This paper introduces a sustainable approach for predicting the mortality risk during the pandemic to help medical decision making and raise public health awareness. This paper describes the range of symptoms for corona virus suffered patients and the ways of predicting patient mortality rate based on their symptoms.

A Forward Selection Method on Customer Credit

In this paper, we discuss a selection and evaluation method of customer credit for the commercial bank loans operation, and put forth a forward selection model by optimization techniques. At last, we also give an example to analyze its application.

A novel OFS–TLBO–SVR hybrid model for optimal budget allocation of government schemes to maximize GVA at factor cost

Support Vector Regression (SVR) has already been proved to be one of the mostreferred and used machine learning technique in various fields. In this study, wehave addressed a predictive-cum-prescriptive analysis for finalizing fundallocations by the Government at center to the schemes under Central Plan andto the schemes under States and Union Territories Plan, with a goal to maximizeGross Value Added (GVA) at factor cost. Here, we have proposed a hybridmachine learning model comprising of OFS (Orthogonal Forward Selection),TLBO (Teaching Learning Based Optimization) and SVR for the prediction ofGVA at factor cost. In this model, referred as OFS–TLBO–SVR hybrid model,SVR is at the core of prediction mechanism, OFS is for identifying the relevantfeatures, and TLBO is to support in optimizing the free parameters of SVR andagain TLBO is used for optimizing the governable attributes of data.