The primary objective of this work is to develop a Neural Network based on LSTM to predict stock market movements using tweets. Word embeddings, used in the LSTM network, are initialised using Stanford's GloVe embeddings, pretrained specifically on 2 billion tweets. To overcome the limited size of the dataset, an augmentation strategy is proposed to split each input sequence into 150 subsets. To achieve further improvements in the original configuration, hyperparameter optimisation is performed. The effects of variation in hyperparameters such as dropout rate, batch size, and LSTM hidden state output size are assessed individually. Furthermore, an exhaustive set of parameter combinations is examined to determine the optimal model configuration. The best performance on the validation dataset is achieved by hyperparameter combination 0.4,8,100 for the dropout, batch size, and hidden units respectively. The final testing accuracy of the model is 76.14%.
This work presents an Artificial Intelligence (AI) system, based on the Faster Region-Based Convolution Neural Network (Faster R-CNN) framework, which detects and counts apples from oblique, aerial drone imagery of giant commercial orchards. To reduce computational cost, a novel precursory stage to the network is designed to preprocess raw imagery into cropped images of individual trees. Unique geospatial identifiers are allocated to these using the perspective projection model. This employs Real-Time Kinematic (RTK) data, Digital Terrain and Surface Models (DTM and DSM), as well as internal and external camera parameters. The bulk of experiments however focus on tuning hyperparameters in the detection network itself. Apples which are on trees and apples which are on the ground are treated as separate classes. A mean Average Precision (mAP) metric, calibrated by the size of the two classes, is devised to mitigate spurious results. Anchor box design is of key interest due to the scale of the apples. As such, a k-means clustering approach, never before seen in literature for Faster R-CNN, resulted in the most significant improvements to calibrated mAP. Other experiments showed that the maximum number of box proposals should be 225; the initial learning rate of 0.001 is best applied to the adaptive RMS Prop optimiser; and ResNet 101 is the ideal base feature extractor when considering mAP and, to a lesser extent, inference time. The amalgamation of the optimal hyperparameters leads to a model with a calibrated mAP of 0.7627.
This work presents a Convolutional Neural Network (CNN) for the prediction of next-day stock fluctuations using company-specific news headlines. Experiments to evaluate model performance using various configurations of word-embeddings and convolutional filter widths are reported. The total number of convolutional filters used is far fewer than is common, reducing the dimensionality of the task without loss of accuracy. Furthermore, multiple hidden layers with decreasing dimensionality are employed. A classification accuracy of 61.7\% is achieved using pre-learned embeddings, that are fine-tuned during training to represent the specific context of this task. Multiple filter widths are also implemented to detect different length phrases that are key for classification. Trading simulations are conducted using the presented classification results. Initial investments are more than tripled over a 838 day testing period using the optimal classification configuration and a simple trading strategy. Two novel methods are presented to reduce the risk of the trading simulations. Adjustment of the sigmoid class threshold and re-labelling headlines using multiple classes form the basis of these methods. A combination of these approaches is found to more than double the Average Trade Profit (ATP) achieved during baseline simulations.