Journal of Emerging Strategies in New Economics

PREDICTING THE INSURANCE CLAIM BY EACH USER USING MACHINE LEARNING ALGORITHMS

Seshu Kumar Vandrangi — Tue, 24 Sep 2024 00:00:00 +0300

Today, data will play a critical role and become a significant wealth creator in the insurance sector. The insurance sector is very significant in today's travel industry. Insurance companies now have more information than ever before. There have been three key eras in the insurance sector over the last 700 years. The manual era lasted from the 15th century to the 1960s, the system age from the 1960s to the 2000s, and now the digital age. H. 2001-20X0. In all three periods, the ultimate corporate objective has been pushed by
the core insurance industry's conviction in data analytics to accept evolving technologies in order to enhance its route and concentrate capital. That's all. Inadequate analytical models and algorithms to serve insurance businesses is a big concern in advanced analytics. Only machines are capable of overcoming this obstacle. In this paper, insurance data based on some features are trained and tested over Artificial Neural Networks, Random Forest Regressors, Logistic Regression and predict the charges based on features for predicting the insurance claim.

PREDICTIONS OF CUSTOMER BEHAVIOUR OVER ECOMMERCE WEBSITES AND ANTICIPATING THEIR INTENTION

Novokhatska Anastasiia — Tue, 24 Sep 2024 00:00:00 +0300

This paper presents a real-time behavioural analytics solution for online consumers that consists of two modules that estimate visitor purchase intent and website desertion probability at the same time. The first module predicts a visitor's purchase intent using aggregated page view statistics acquired during a visit as well as certain session and user information. The collected features are fed into classifiers such as random forest (RF), support vector machine (SVM), and multilayer perceptron (MLP). To increase classifier performance and scalability, use oversampling and feature selection pre-processing processes. The findings reveal that MLP calculated with a robust backpropagation method with weight backtracking outperforms RF and SVM in terms of accuracy and F1 score. Another discovery is that, although clickstream data gathered from online navigation patterns transmit vital information about visitor buy intent, session information bases include unique information about purchasing inclinations. In the second module, everyone estimate the likelihood of a visitor's desire to exit the website without completing a purchase using just sequential clickstream data. Everyone trains a long short-term memory-based recurrent neural network to provide a sigmoidal output indicating the predicted horizon. When used together, the modules detect visitors who are ready to make a purchase but are likely to depart the site within the forecast time and take the necessary steps to enhance website abandonment and buy conversion rates to do. Our findings indicate the viability of employing clickstream and session information data to forecast purchase intent in virtual retail environments in an accurate and scalable manner.

STOCK PRICE PREDICTION FROM NEWS HEADLINES USING MACHINE LEARNING MODELS

Ahmed J. Obaid — Tue, 24 Sep 2024 00:00:00 +0300

It's a tremendously intriguing and exciting issue to forecast and speculate on stock market values, especially worldwide company values. This article uses economic news received from businesses to discuss changes in stock prices and projections of stock values. Pay attention to business news headlines and assess headline sentiment using a number of tactics. The Neural Network reconstructs sentiment outcomes with changes in equities over the same period by using BERT as a benchmark and comparing the findings with three other tools. Compared to the other two tools, BERT and RNN are substantially more accurate since they can recognise emotional values without the neutral component. Establish when changes in stock values occur by contrasting these findings with stock value fluctuations over the same time period using sentiment analysis of economic news articles. The impact of sentimental value on changes in sentimental stock market value was also shown to vary significantly amongst the various models.

STOCK PRICE PREDICTION USING TIME SERIES FORECASTING BY MACHINE LEARNING MODELS

Sajaratuddur, Lelya Hilda — Tue, 24 Sep 2024 00:00:00 +0300

It is a highly obvious fact that, the stock market is a fickle beast, and making forecasts may be difficult. Stock prices are impacted by both economic and non-economic variables. Refers to several essential physical, psychological, rational, and so on factors. The stock price is predicted using the autoregressive integrated migration Average (ARIMA) model in this research article. have a model for predicting stock prices. Create and disseminate obtained inventory data from Yahoo Finance on a regular basis. The experimental findings show that ARIMA models may be used to accurately estimate inventory levels and short-term pricing.

GDP PREDICTION FOR COUNTRIES USING MACHINE LEARNING MODELS

Gurunadh Velidi — Tue, 24 Sep 2024 00:00:00 +0300

The significance of GDP is demonstrated by the fact that it offers data on the size and functioning of an economy. Real GDP growth is frequently used as a measure of the state of the economy as a whole. Real GDP growth is typically regarded as a positive indicator of the state of the economy. The goal of this research is to forecast global GDP and determine its annual growth rate using machine learning. Since GDP varies from year to year, it is crucial to understand the status and importance of the variables that influence a
country's GDP now. If you depict this in a diagram, it will be simpler to grasp. Additionally, the significance of the impacted parameters in determining GDP is calculated in this research-based study. Viewers may easily compare the GDP growth rates of other nations as well as their best and worst performance predictions. In this study, by using a variety of machine learning algorithms to analyse the global GDP.