Ensemble and Multimodal Approach for Forecasting Cryptocurrency Price

Since the birth of Bitcoin in 2009, cryptocurrencies have emerged to become a global phenomenon and an important decentralized financial asset. Due to this decentralization, the value of these digital currencies against fiat currencies is highly volatile over time. Therefore, forecasting the crypto-fiat currency exchange rate is an extremely challenging task. For reliable forecasting, this paper proposes a multimodal AdaBoost-LSTM ensemble approach that employs all modalities which derive price fluctuation such as social media sentiments, search volumes, blockchain information, and trading data. To better support investment decision making, the approach forecasts also the fluctuation distribution. The conducted extensive experiments demonstrated the effectiveness of relying on multimodalities instead of only trading data. Further experiments demonstrate the outperformance of the proposed approach compared to existing tools and methods with a 19.29% improvement.

Multimodal Approach for Metadata Extraction from German Scientific Publications

Nowadays, metadata information is often given by the authors themselves upon submission. However, a significant part of already existing research papers have missing or incomplete metadata information. German scientific papers come in a large variety of layouts which makes the extraction of metadata a non-trivial task that requires a precise way to classify the metadata extracted from the documents. In this paper, we propose a multimodal deep learning approach for metadata extraction from scientific papers in the German language. We consider multiple types of input data by combining natural language processing and image vision processing. This model aims to increase the overall accuracy of metadata extraction compared to other state-of-the-art approaches. It enables the utilization of both spatial and contextual features in order to achieve a more reliable extraction. Our model for this approach was trained on a dataset consisting of around 8800 documents and is able to obtain an overall F1-score of 0.923.