Statistical methods were traditionally primarily used for time series forecasting. However, new hybrid methods demonstrate competitive accuracy, leading to increased machine-learning-based methodologies in the financial sector. However, very little development has been seen in explainable AI (XAI) for financial time series prediction, with a growing mandate for explainable systems. This study aims to determine if the existing XAI methodology is transferable to the context of financial time series prediction. Four popular methods, namely, ablation, permutation, added noise, and integrated gradients, were applied to a recurrent neural network (RNN), long short-term memory (LSTM), and a gated recurrent unit (GRU) network trained on S&P 500 stocks data to determine the importance of features, individual data points, and specific cells in each architecture. The explainability analysis revealed that GRU displayed the most significant ability to retain long-term information, while the LSTM disregarded most of the given input and instead showed the most notable granularity to the considered inputs. Lastly, the RNN displayed features indicative of no long-term memory retention. The applied XAI methods produced complementary results, reinforcing paradigms on significant differences in how different architectures predict. The results show that these methods are transferable in the financial forecasting sector, but a more sophisticated hybrid prediction system requires further confirmation.

Among the numerous biological constraints that hinder cassava (Manihot esculenta Crantz) production, foremost is cassava mosaic disease (CMD) caused by virus members of the family Geminiviridae, genus Begomovirus. The mechanisms of CMD tolerance and susceptibility are not fully understood; however, CMD susceptible T200 and tolerant TME3 cassava landraces have been shown to exhibit different large-scale transcriptional reprogramming in response to South African cassava mosaic virus (SACMV). Recent identification of 85 MeWRKY transcription factors in cassava demonstrated high orthology with those in Arabidopsis, however, little is known about their roles in virus responses in this non-model crop. Significant differences in MeWRKY expression and regulatory networks between the T200 and TME3 landraces were demonstrated. Overall, WRKY expression and associated hormone and enriched biological processes in both landraces reflect oxidative and other biotic stress responses to SACMV. Notably, MeWRKY11 and MeWRKY81 were uniquely up and downregulated at 12 and 67 days post infection (dpi) respectively in TME3, implicating a role in tolerance and symptom recovery. AtWRKY28 and AtWRKY40 homologs of MeWRKY81 and MeWRKY11, respectively, have been shown to be involved in regulation of jasmonic and salicylic acid signaling in Arabidopsis. AtWRKY28 is an interactor in the RPW8-NBS resistance (R) protein network and downregulation of its homolog MeWRKY81 at 67 dpi in TME3 suggests a negative role for this WRKY in SACMV tolerance. In contrast, in T200, nine MeWRKYs were differentially expressed from early (12 dpi), middle (32 dpi) to late (67 dpi) infection. MeWRKY27 (homolog AtWRKY33) and MeWRKY55 (homolog AtWRKY53) were uniquely up-regulated at 12, 32 and 67 dpi in T200. AtWRKY33 and AtWRKY53 are positive regulators of leaf senescence and oxidative stress in Arabidopsis, suggesting MeWRKY55 and 27 contribute to susceptibility in T200.