2019/05/23 by Jérémy Charlier, Charlier, Jeremy, Radu State +3
Computer Science · Mathematics · #Algorithms and Data Compression #Computational Engineering #FOS: Computer and information sciences #FOS: Mathematics #Finance #Numerical Analysis (math.NA) #Parallel Computing and Optimization Techniques #Tensor decomposition and applications #and Science (cs.CE)
paper · pdf · doi:10.48550/arxiv.1905.09869
openalex publication_date 2019/05/23 · openalex created_date 2022/07/29 · openalex updated_date 2026/07/28
Smart contracts are programs stored and executed on a blockchain. The\nEthereum platform, an open-source blockchain-based platform, has been designed\nto use these programs offering secured protocols and transaction costs\nreduction. The Ethereum Virtual Machine performs smart contracts runs, where\nthe execution of each contract is limited to the amount of gas required to\nexecute the operations described in the code. Each gas unit must be paid using\nEther, the crypto-currency of the platform. Due to smart contracts interactions\nevolving over time, analyzing the behavior of smart contracts is very\nchallenging. We address this challenge in our paper. We develop for this\npurpose an innovative approach based on the non-negative tensor decomposition\nPARATUCK2 combined with long short-term memory (LSTM) to assess if predictive\nanalysis can forecast smart contracts interactions over time. To validate our\nmethodology, we report results for two use cases. The main use case is related\nto analyzing smart contracts and allows shedding some light into the complex\ninteractions among smart contracts. In order to show the generality of our\nmethod on other use cases, we also report its performance on video on demand\nrecommendation.\n