National Repository of Grey Literature 2 records found  Search took 0.00 seconds. 
Predicting purchasing intent on ecommerce websites
Vařeka, Marek ; Krištoufek, Ladislav (advisor) ; Baruník, Jozef (referee)
This thesis analyzes behavior of customers on an e-commerce website in order to predict whether the customer is willing to buy something or is just window shopping. In addition the secondary model predicts, if the customer is going to leave the e-commerce website in next few clicks. To answer this questions different frameworks are tested. The base model used is the Logit model. The base model is compared with more sophisticated methods in machine learning - with neural networks. The best results were yielded by Recurrent neural network - the Long Short-Term Memory (LSTM). The results of the analysis confirm importance of the click stream data and calculated features that track user behavior on the e-commerce website, type of the page (product, category, information), product variance and category variance. The thesis emphasizes practical implications of this models. Two possible practical implementations are presented. The models are tested in novel ways to see how would they perform if implemented on the real e-commerce website.
Can the stock markets predict changes in macroeconomic variables?
Vařeka, Marek ; Krištoufek, Ladislav (advisor) ; Hayat, Arshad (referee)
A bstract There is a consensus in the literature, that the stock market can predict the Gross domestic product on quarterly base or the industrial production, which is good proxy for GDP, on monthly basis and that the causal rela­ tionship between stock market and GDP should work both ways. However, using Vector autoregression model on US data since 1950, model shows that the stock market can not only predict the Industrial production on monthly basis, but also ISM non-manufacturing index, which is a good proxy for services in the economy. Furthermore I have managed to prove, that the unemployment can be predicted by past realizations of the stock market and managed to explain almost one third of all variations in change in un­ employment using S&P500 and oil prices during last 20 years. The Granger causality test concluded that stock market does cause the unemployment but not vice versa, at least during last 20 years.

See also: similar author names
2 Vařeka, Miloš
Interested in being notified about new results for this query?
Subscribe to the RSS feed.