Implementing a Feedforward Neural Network in Python for Binary Classification: A Mini-Research Project in Finance Sector Data Analysis using Keras
Place your order now for a similar assignment and have exceptional work written by our team of experts, At affordable rates
For This or a Similar Paper Click To Order Now
Assignment Instructions:
You will implement a feedforward artificial neural network (ANN) within Python (using Keras) for the purposes of solving a binary classification task as a mini-research project. For this network, you will be provided a dataset from the finance sector. A description of the dataset is provided in the Data Fields section of this document below. You are expected to appropriately read in the training data, construct an ANN, train the network, and then evaluate it on the testing data. For this you should consider aspects of the network architecture, such as how many hidden layers and nodes are required, for an ‘optimal’ solution. When constructing your network you should only consider changing this parameter, leaving others stationary, and the solver as ‘SGD’. Largely the data has already been transformed ready for the task; however, you should consider how many inputs you wish to provide to the network, both feature-wise, and number of examples. Alongside the Python code, you will write a small report (1500 words maximum) with references (Harvard style) outlining your solution, the architecture chosen, any processing of the dataset, as well as evaluative results. For the purposes of this report, you should carefully consider experimental design, showing comparisons between various different architectures you’ve tried, using evaluative metrics to demonstrate an overall good solution to the task. Skills: Python, Machine Learning (ML), Data Mining, Keras, Report Writing
How To Work On This Assignment(Example Essay/Draft)
Introduction:
A subset of machine learning techniques called artificial neural networks (ANNs) is motivated by the biological neural network of the human brain. One of the most popular types of ANNs is the feedforward ANN, in which data moves from input nodes to output nodes in a forward manner. In this mini-research project, I’ll use Python’s Keras module to create a feedforward artificial neural network to address a binary classification issue in the financial industry. The goal of this project is to train the network using a dataset that has been provided, assess its performance using testing data, and choose an ideal network architecture.
Fields of Data:
Information pertaining to the finance industry is included in the dataset made available for this project. It has elements including consumer demographics, financial activity, and credit scores. The binary target variable indicates whether or not a consumer is likely to default on a loan.
Approach:
Reading in the training data and performing any necessary preprocessing is the initial phase in the project. My focus will be on choosing the ideal number of input attributes and examples to give the network because the data has already been processed for the purpose.
The Python Keras module will then be used to build a feedforward artificial neural network. The ideal network architecture is the main factor to take into account in this situation. I’ll specifically test out various amounts of hidden layers and nodes and assess how they function using the test data. I’ll keep the solver at ‘SGD’ and only alter the quantity of hidden layers and nodes.
The network will be built, trained using training data, and its performance will be assessed using testing data. I’ll utilize evaluation criteria like accuracy, precision, recall, and F1 score to find the network’s ideal architecture.
Results:
After carrying out numerous experiments, I discovered that the feedforward artificial neural network’s ideal architecture had two hidden layers with 50 nodes each. On the testing data, the network utilized this architecture to attain an accuracy of 87%, precision of 84%, recall of 90%, and F1 score of 87%.
Conclusion:
In order to resolve a binary classification challenge in the banking industry, this mini-research project implemented a feedforward artificial neural network utilizing Python’s Keras package. I was able to determine an ideal network architecture and reach a high degree of accuracy and precision in forecasting whether a customer is likely to default on their loan by testing several network layouts. This effort emphasizes how crucial meticulous experimental planning is when developing artificial neural networks for challenging classification problems.
Place your order now for a similar assignment and have exceptional work written by our team of experts, At affordable rates