Diabetes Risk Forecasting Using Logistic Regression

Diabetes can be a collection of metabolic problems and lots of human beings are affected. Diabetes Mellitus can be caused by a variety of factors including age, stoopedness, lack of activity, inherited diabetes, lifestyle, poor eating habits, hypertension, and so on. Diabetics are more likely to develop diseases like coronary illness, kidney contamination, eye sickness, stroke and other risks. Distributed computing and Internet of Things (IoT) are two instruments that assume a vital part in the present life with respect to numerous angles and purposes including medical care observing of patients and old society. Diabetes Healthcare Monitoring Services are vital these days on the grounds that and that to distant medical care observing in light of the fact that truly going to clinics and remaining in a line is exceptionally ineffectual adaptation of patient checking. Current practice in emergency clinic is to gather required data for diabetes conclusion through different tests and proper treatment is given dependent on analysis. Utilizing enormous data investigation can consider large datasets and discover covered up data, uncertain examples to find information from the data and expect the outcome as demand. Diabetics are caused because of a tremendous uphill in the blood partition containing glucose. There is an advancement conspire accessible using train test split and K overlay cross approval utilizing Scikit learn technique. Various ML algorithms consisting of SVM, RF, KNN, NB, Decision Tree and Logistic Regression are also used.

Method of Assessing the Risk of Implementing Railway Investments in Terms of the Cost of Their Implementation

Exceeding the approved budget is often an integral part of the implementation of construction projects, especially those where unforeseen threats may occur. Therefore, each construction investment should contain elements of risk forecasting, mainly in terms of the cost of its implementation. Only a small number of institutions apply effective cost control methods, taking into account the specifics of a given industry. Especially small construction companies that participate in the structure of the implementation of large construction projects as subcontractors. The article presents a method by which it is possible to determine, with certain probability, the final cost of railway construction investments carried out in Poland. The method was based on a reliable database of risk factors published in sources. In this article, the main presumptions of the original method are presented, which take into account the impact of potential, previously recognized, risks specific to railway investments, and enable project managers to relate them to the conditions where the implementation of a specific object is planned. The authors assumed that such a relatively simple method, supported by a suitable computational program, would encourage teams that plan to implement railway projects to use it and increase the credibility of their schedules.

Neural network approximation in forecasting economic risks

The article considers methodological approaches to assessing the level of development of economic systems in the context of increasing the accuracy of forecasts in unpredictable socio-economic conditions in particular taking into account the impact of unforeseen environmental risks and disasters. The authors used methods to approximate economic criteria with the help of neural networks. Analyzing the criteria of economic development of different countries, as well as taking into account the factors of the macroeconomic environment, a neural network approximation model of risk forecasting in the economic development of the country has been developed. To date, a large number of mathematical forecasting methods are known, and experts in the world economy use appropriate risk assessment criteria, but the neural network is used when the exact type of connections between inputs and outputs is unknown, which allows us to create a more accurate and flexible forecast model. The modeling takes into account the main weights that determine the degree and the priority of the impact on each component of the economic system and characterizes the complex macroeconomic relationships to determine the aggregate indices.

Analysis and Forecasting of Risk in Count Processes

Risk measures are commonly used to prepare for a prospective occurrence of an adverse event. If we are concerned with discrete risk phenomena such as counts of natural disasters, counts of infections by a serious disease, or counts of certain economic events, then the required risk forecasts are to be computed for an underlying count process. In practice, however, the discrete nature of count data is sometimes ignored and risk forecasts are calculated based on Gaussian time series models. But even if methods from count time series analysis are used in an adequate manner, the performance of risk forecasting is affected by estimation uncertainty as well as certain discreteness phenomena. To get a thorough overview of the aforementioned issues in risk forecasting of count processes, a comprehensive simulation study was done considering a broad variety of risk measures and count time series models. It becomes clear that Gaussian approximate risk forecasts substantially distort risk assessment and, thus, should be avoided. In order to account for the apparent estimation uncertainty in risk forecasting, we use bootstrap approaches for count time series. The relevance and the application of the proposed approaches are illustrated by real data examples about counts of storm surges and counts of financial transactions.