Bilgisayar Mühendisliği Bölümü Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.11779/1940

Browse

Filters

20232

Settings

Language: search.filters.language.trSubject: search.filters.subject.Deep learning

Search Results

Now showing 1 - 2 of 2
  • Conference Object
    Noise Effect on Forecasting
    (IEEE, 2023) Tuncer, Suat; Çakar, Tuna; Çakar, Tuna; 02.02. Department of Computer Engineering; 02. Faculty of Engineering; 01. MEF University
    The lack of regulation and liquidity in crypto money markets causes higher volatility compared to other financial markets. This situation increases the noise in price change. The high noise and random walk create a problem that cannot be explained by traditional stochastic financial methods. For this reason, a multi-layered deep learning model with an additive attention layer, which uses a single observation in 10-day sequences, was used in this study. Different transformations are used to reduce the noise of the closing values. As a result of the comparisons made between different approaches, it has been revealed that exponential moving averages, to be used as the value to predict, give better results than other conversions and estimation of the original price, since they explain the price better than simple moving averages and reduce the noise of the original price.
  • Conference Object
    Transaction Volume Estimation in Financial Markets With Lstm
    (IEEE, 2023) Bozkan, Tunahan; Çakar, Tuna; Ertuğrul, Seyit; Sayar, Alperen; Akçay, Ahmet; 02.02. Department of Computer Engineering; 02. Faculty of Engineering; 01. MEF University
    In this study, it was aimed to determine the transaction volume that will be encountered in the future (hourly) in the factoring sector, and then to take financial and operational action early. For the study, the LSTM model, which is a kind of recurrent neural network (RNN) that can capture long and short-term dependencies, was applied by using data-driven approaches to estimate the check amounts of hourly transactions. As a result of the results, it was aimed to increase the operational efficiency in a broad scope by allowing the factoring company to determine the loan amounts to be obtained from banks in the most optimal way, and then to take early action within the scope of both the workforce and business management of the financial resource allocation management process and operational activities. MAPE score was used as a measure of error in the time series analysis model. MAPE scores were found as %5.05 for 30 days, %4.18 for 10 days, %3.47 for 5 days, %3.09 for 3 days and %1.83 for 1 day. According to the MAPE scores calculated for different days, the enterprise will be able to decide on the loan to be drawn from banks both in terms of time and amount, and the necessary action will be taken.