Reference no: EM133085315
MSc Programme - Big Data
Project Specification
Research Question 1: What are the appropriate actions in order to prevent the money laundering bank transaction.
Research Question 2: Up-to which Extent level of Algorithm will work to Detect and Identify money laundering.
Research Question 3: Which is the better machine learning algorithm among Decision tree and K Nearest Neighbour in Identifying money laundering bank transaction.
Outline overview and overall aim of Project:
Money laundering is the most dangerous and effects country's economy and, It's a negative energy to the society. The money participated in money laundering transactions is an Illegal money. This money raised by doing illegal activities such as drug matte. Money laundering encourages terrorist activities, and these activities needs huge amount. The needed huge amount divides Into small chunks and send It to target through different bank transactions.
There are many techniques and systems emerged to find out the money laundering activities and these systems called as Anti-Money Laundering (AMU systems. The traditional AML systems consist of lot of rules to verify a transaction and gives false results.
To overcome this now machine learning algorithms are used in AML systems. Decision tree and K-means are the most used algorithms in AML systems.
The aim of this research is to find the better algorithm between Decision tree and K-means. This would be done by applying two algorithms on the Money Laundering data set. The data set divided into two parts such as testing and training datasets. Both algorithms get trained and tested. Testing algorithms results accuracy. Comparison of accuracy is the better algorithm will be stated.
Objectives (list of tasks to be undertaken to achieve overall aim of the project and to answer the research question posed):
1. Information gathering about previous research works from Journals, articles, and research papers.
2. Data set exploring (Kaggle, Google Research Dataset) and analyzing the attributes of the data set data.
3. Updating the data set to suit for the research.
4. Developing the model.
5. Testing the model using test data.
6. Comparing the algorithms based on the accuracy.
Relationship of proposed project to MSc programme/stream:
The proposed project is about data mining and machine learning. My stream Is "Advance Computing: Big Data" which includes Data mining, Advance data science, Emerging techniques, Research design and methodology modules.
Attachment:- Big Data - Project specification.rar