Intelligent Log Analysis for Anomaly Detection By Steven Yen Computer logs are a rich source of information that can be analyzed to detect various issues. The large volumes of logs limit the effectiveness of manual approaches to log analysis. The earliest automated log analysis tools take a rule-based approach, which can only detect known issues with existing rules. On the other hand, anomaly detection approaches can detect new or unknown issues. This is achieved by looking for unusual behavior different from the norm, often utilizing machine learning (ML) or deep learning (DL) models. In this project, we evaluated various ML and DL techniques used for log anomaly detection. We propose a hybrid neural network (NN) we call "CausalConvLSTM" for modeling log sequences, which takes advantage of both Convolutional Neural Network and Long Short-Term Memory Network's strengths. Furthermore, we evaluated and proposed a concrete strategy for retraining NN anomaly detection models to maintain a low false-positive rate in a drifting environment. 4 ACKNOWLEDGEMENTS This master's project has been a substantial undertaking for me, and I would like to thank my project advisor Dr. Melody Moh for all her support and guidance through the entire process, from my initial project selection, to development, to completion. I would like to thank Dr. Teng Moh for all the feedback and insights he has provided throughout the development of the project. I would like to thank Professor Auston Davis and Dr. Katerina Potika for serving as my committee members, and spending time to discuss the project with me and sharing ideas and other considerations. I would like to thank all the CS department faculty members and my friends at SJSU for making my pursuit of a master's degree more fulfilling and pleasant. Finally, I would like to thank my family for always being there for me.