Prediction of Transaction Confirmation Time in Ethereum Blockchain Using Machine Learning

Abstract

Blockchain offers a decentralized, immutable, transparent system of records. It offers a peer-to-peer network of nodes with no centralised governing entity making it 'unhackable' and therefore, more secure than the traditional paper-based or centralised system of records like banks etc. While there are certain advantages to the paper-based recording approach, it does not work well with digital relationships where the data is in constant flux. Unlike traditional channels, governed by centralized entities, blockchain offers its users a certain level of anonymity by providing capabilities to interact without disclosing their personal identities and allows them to build trust without a third-party governing entity. Due to the aforementioned characteristics of blockchain, more and more users around the globe are inclined towards making a digital transaction via blockchain than via rudimentary channels. Therefore, there is a dire need for us to gain insight on how these transactions are processed by the blockchain and how much time it may take for a peer to confirm a transaction and add it to the blockchain network. This paper presents a novel approach that would allow one to estimate the time, in block time or otherwise, it would take for a mining node to accept and confirm a transaction to a block using machine learning. The paper also aims to compare the predictive accuracy of two machine learning regression models-Random Forest Regressor and Multilayer Perceptron against previously proposed statistical regression model under a set evaluation criterion. The objective is to determine whether machine learning offers a more accurate predictive model than conventional statistical models. The proposed model results in improved accuracy in prediction.

Proposal of an Economy of Things Architecture and an Approach Comparing Cryptocurrencies

“…This definition is a critical step, as high amounts paid can make the transaction be confirmed faster and waste tokens, while lower amount transactions can never be confirmed. As it is possible to see in [27], between 2017 and 2019, the average time of the blocks was near of 15 s. Figure 8 shows that the average time for requests with only one thread, using the network's average GAS price, was within the expected, making the transaction be placed in the first two blocks. Even though in some cases the average for transactions with a lower GAS value was lower, in Figure 9 it is possible to see the behavior when placing a GAS value that is too low.…”

A user-oriented model for Oracles’ Gas price prediction

“…The miners have full control over their transaction pool and may adopt different policies to manage it. For instance, a miner could set up a minimum fee threshold, thus transactions with a Gas price lower than the threshold are immediately discarded from the transaction pool and only the new transactions with a price higher than the threshold are allowed to enter the transaction pool [29].…”

“…In a previous study [28], Singh and Hafid proposed a more fine-grained classification model when compared to the existing Gas Oracles' classification. The model split the inclusion time of transactions into eight classes: respectively within 15 seconds, 30 seconds, 1 minute, 2 minutes, 5 minutes, 10 minutes, 15 minutes, and 30 minutes or longer.…”

Are the Gas Prices Oracle Reliable? A Case Study using the EthGasStation

“…Singh and Hafid [10] proposes a more fine-grained classification model that splits the confirmation time of transactions into eight classes: within 15 seconds, within 30 seconds, within 1 minute, within 2 minutes, within 5 minutes, within 10 minutes, within 15 minutes and within 30 minutes or longer. We know that on average, a transaction has to wait for two block confirmations (∼30 seconds) before being added.…”

“…It can only provide a user with an approximation of time it would take for their transaction to be confirmed, which may or may not always be ideal. In addition, Singh and Hafid [10] compare the performance of two machine learning regression models (Multi-Layer Perceptron and Random Forest) and the more classical, statistical model (Poisson Regression) on the task of predicting the confirmation time for a transaction in Ethereum Blockchain. The authors suggest that machine learning regression models perform well and better than the already used statistical approach.…”