Neural Networks (NNs)
Overview
Neural Networks (NNs) are a type of machine learning algorithm modeled after the structure and function of the human brain. They consist of layers of interconnected nodes or neurons that process and transmit information, using mathematical operations to learn patterns and relationships in the input data. NNs can be used for a wide range of tasks, such as image recognition, natural language processing, and prediction.
Recurrent Neural Networks (RNNs) are a type of Neural Network that can process sequential data, such as time-series or text data. They use feedback connections to pass information from one time step to another, allowing them to model long-term dependencies in the input data.
Long Short-Term Memory Networks (LSTMs) are a type of RNN that are specifically designed to address the problem of vanishing gradients in traditional RNNs. LSTMs use a gated architecture to selectively pass information from one time step to another, allowing them to learn long-term dependencies more effectively.
Convolutional Neural Networks (CNNs) are a type of Neural Network that are commonly used for image and video recognition tasks. They use convolutional layers to learn local features in the input data, which are then combined to form higher-level representations of the input.
Artificial Neural Networks (ANNs) are a type of Neural Network that are composed of multiple layers of interconnected nodes or neurons. They are often used for supervised learning tasks, such as classification and regression, and can be trained using a variety of optimization algorithms, such as backpropagation.
In the context of analyzing brand recognition and customer appeal in the footwear market, each of these Neural Network architectures could be used to model different aspects of the input data. For example, a CNN could be used to learn local features in images of shoes, an RNN could be used to model temporal dependencies in customer review data, and an ANN could be used to predict customer appeal based on a combination of different input features. An example image of a simple Neural Network architecture is shown below:
​
Data Preparation
Neural Networks (NNs) are a type of machine learning algorithm that requires labeled data for supervised learning methods. Labeled data refers to data that has been assigned a specific output or target label that the NN is trying to predict. In the context of analyzing brand recognition and customer appeal in the footwear market, labeled data could include images of shoes that are assigned a specific brand label or customer reviews that are labeled as positive or negative based on the sentiment.
Code
Results
Confusion Matrix And Accuracy
Recurrent Neural Networks (RNNs) ​
Convolutional Neural Networks (CNNs)
Long Short-Term Memory Networks (LSTMs)
Conclusion
The conclusions that were drawn provided valuable insights into the market position of Nike and its competitors. The NN models were able to predict the likelihood of customers recognizing and favorably responding to Nike's brand compared to other shoe brands, as well as identify the key features or factors that contributed to brand recognition and customer appeal. The results of the analysis shed light on whether Nike was the top-ranked brand in the global footwear market and how it compared to its competitors in terms of brand recognition and customer appeal.