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.
Deep Dive into Transaction Confirmation Time Prediction in Ethereum Blockchain Using Machine Learning.
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 proces
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.
Index
terms--
Blockchain,
Confirmation
Time,
Ethereum,
Machine
Learning,
Regression,
Transaction,
Multilayer
Perceptron (MLP), Random Forest.
I. INTRODUCTION
Blockchain Technology is a distributed database
shared between nodes in a peer-to-peer network (e.g.,
more than 10000 nodes in Ethereum). Basically, each
network node can receive and broadcast transactions.
Blockchain, as the name suggests, records transactions
into linked blocks [1]. When a user wants to interact
with the blockchain (e.g., to transfer cryptocurrency or
store a testament), they create and sign, using their
private key, a transaction; note that blockchain, in
itself, uses public key encryption. Then, it sends the
transaction to the blockchain network; a node that
receives the transaction, validates the transactions
(e.g., verifies the user’s signature) and, if valid, stores
the transaction in its pending list of transactions and
transmits it to its neighbouring nodes. Periodically, a
node is selected to create a block; the selection is based
on the consensus protocol in use. In the case of proof-
of-work (PoW) consensus protocol [2], the node that
first solves a mathematical puzzle, is the one that
creates the new block. It is important to emphasize that
there should be no shortcuts to solve the puzzle in
order to guarantee that nodes are selected randomly.
PoW consists of determining a string (called nonce)
such that when combined with the block header and
hashed results in hash that includes a given number of
leading 0 bits (this number represents the difficulty in
solving the puzzle). Nodes are incentivised to create
new blocks because they are rewarded by newly
minted coins (e.g., in the bitcoin blockchain, the
reward is 12.5 bitcoins as of 2019) and transactions
fees. The time it takes to generate a block, called block
time, is specific to the blockchain in use; for example,
the block time for bitcoin is 10 minutes whereas it is
15 seconds for Ethereum.
Transaction Confirmation Time Prediction in Ethereum Blockchain Using
Machine Learning
Harsh Jot Singh, Abdelhakim Senhaji Hafid, Department of Computer Science and Operational
Research, University of Montreal, Montreal, QC H3T 1J4
Blockchain comes in many different types. More
specifically, there are three types of blockchains:
permissionless blockchain also known as public
blockchain (e.g., Bitcoin and Ethereum), permissioned
blockchain also known as consortium blockchain (e.g.,
Hyperledger fabric), and private blockchain. In public
blockchains, any participant/user can write data to the
blockchain and can read data recorded in the
blockchain; anybody can be a full node, a miner or a
light node. Thus, there is little to no privacy for
recorded data and there are no regulations or rules for
participants to join the network. Generally, pubic
blockchains are considered pseudo-anonymous (e.g.,
bitcoin and Ethereum); a participant does not have to
divulge their identity (e.g., name) instead the user is
linked to an address (i.e., hash of public key).
Providing anonymity is difficult but it is feasible (e.g.,
Zcash
…(Full text truncated)…
This content is AI-processed based on ArXiv data.