ALBERT

Description: Exchange rate forecasting has been an important topic for investors, researchers, and analysts. In this study, financial sentiment analysis (FSA) and time series analysis (TSA) are proposed to form a predicting model for US Dollar/Turkish Lira exchange rate. For this purpose, the proposed hybrid model is constructed in three stages: obtaining and modeling text data for FSA, obtaining and modeling numerical data for TSA, and blending two models like a symmetry. To our knowledge, this is the first study in the literature that uses social media platforms as a source for FSA and blends them with TSA methods. To perform FSA, word embedding methods Word2vec, GloVe, fastText, and deep learning models such as CNN, RNN, LSTM are used. To the best of our knowledge, this study is the first attempt in terms of performing the FSA by using the combinations of deep learning models with word embedding methods for both Turkish and English texts. For TSA, simple exponential smoothing, Holt–Winters, Holt’s linear, and ARIMA models are employed. Finally, with the usage of the proposed model, any user who wants to make a US Dollar/Turkish Lira exchange rate forecast will be able to make a more consistent and strong exchange rate forecast.

Description: Nowadays, smart devices as a part of daily life collect data about their users with the help of sensors placed on them. Sensor data are usually physical data but mobile applications collect more than physical data like device usage habits and personal interests. Collected data are usually classified as personal, but they contain valuable information about their users when it is analyzed and interpreted. One of the main purposes of personal data analysis is to make predictions about users. Collected data can be divided into two major categories: physical and behavioral data. Behavioral data are also named as neurophysical data. Physical and neurophysical parameters are collected as a part of this study. Physical data contains measurements of the users like heartbeats, sleep quality, energy, movement/mobility parameters. Neurophysical data contain keystroke patterns like typing speed and typing errors. Users’ emotional/mood statuses are also investigated by asking daily questions. Six questions are asked to the users daily in order to determine the mood of them. These questions are emotion-attached questions, and depending on the answers, users’ emotional states are graded. Our aim is to show that there is a connection between users’ physical/neurophysical parameters and mood/emotional conditions. To prove our hypothesis, we collect and measure physical and neurophysical parameters of 15 users for 1 year. The novelty of this work to the literature is the usage of both combinations of physical and neurophysical parameters. Another novelty is that the emotion classification task is performed by both conventional machine learning algorithms and deep learning models. For this purpose, Feedforward Neural Network (FFNN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) neural network are employed as deep learning methodologies. Multinomial Naïve Bayes (MNB), Support Vector Regression (SVR), Decision Tree (DT), Random Forest (RF), and Decision Integration Strategy (DIS) are evaluated as conventional machine learning algorithms. To the best of our knowledge, this is the very first attempt to analyze the neurophysical conditions of the users by evaluating deep learning models for mood analysis and enriching physical characteristics with neurophysical parameters. Experiment results demonstrate that the utilization of deep learning methodologies and the combination of both physical and neurophysical parameters enhances the classification success of the system to interpret the mood of the users. A wide range of comparative and extensive experiments shows that the proposed model exhibits noteworthy results compared to the state-of-art studies.

Description: Demand forecasting is one of the main issues of supply chains. It aimed to optimize stocks, reduce costs, and increase sales, profit, and customer loyalty. For this purpose, historical data can be analyzed to improve demand forecasting by using various methods like machine learning techniques, time series analysis, and deep learning models. In this work, an intelligent demand forecasting system is developed. This improved model is based on the analysis and interpretation of the historical data by using different forecasting methods which include time series analysis techniques, support vector regression algorithm, and deep learning models. To the best of our knowledge, this is the first study to blend the deep learning methodology, support vector regression algorithm, and different time series analysis models by a novel decision integration strategy for demand forecasting approach. The other novelty of this work is the adaptation of boosting ensemble strategy to demand forecasting system by implementing a novel decision integration model. The developed system is applied and tested on real life data obtained from SOK Market in Turkey which operates as a fast-growing company with 6700 stores, 1500 products, and 23 distribution centers. A wide range of comparative and extensive experiments demonstrate that the proposed demand forecasting system exhibits noteworthy results compared to the state-of-art studies. Unlike the state-of-art studies, inclusion of support vector regression, deep learning model, and a novel integration strategy to the proposed forecasting system ensures significant accuracy improvement.