Position: What Can Large Language Models Tell Us about Time Series Analysis
Authors: Ming Jin, Yifan Zhang, Wei Chen, Kexin Zhang, Yuxuan Liang, Bin Yang, Jindong Wang, Shirui Pan, Qingsong Wen
ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | This subsection presents experiments evaluating the LLM s zero-shot capability as an agent for human interaction and time series data analysis. We utilize the HAR (Anguita et al., 2013) database, derived from recordings of 30 study participants... The prompts used for GPT-3.5 are illustrated in Figure 8, and the classification confusion matrix is presented in Figure 5. |
| Researcher Affiliation | Collaboration | 1Griffith University. 2Chinese Academy of Sciences. 3The Hong Kong University of Science and Technology (Guangzhou). 4Zhejiang University. 5East China Normal University. 6Microsoft Research Asia. 7Squirrel AI. |
| Pseudocode | Yes | The prompts used for GPT-3.5 are illustrated in Figure 8, and the classification confusion matrix is presented in Figure 5. Figure 8: Human interaction with Chat GPT for time series classification task. Figure 9: Human interaction with Chat GPT for time series data augmentation and anomaly detection tasks. These figures show the step-by-step interaction with the LLM, representing the procedure. |
| Open Source Code | No | The paper does not contain an explicit statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | We utilize the HAR (Anguita et al., 2013) database, derived from recordings of 30 study participants engaged in activities of daily living (ADL) while carrying a waist-mounted smartphone with embedded inertial sensors. |
| Dataset Splits | No | The paper mentions 'The end goal is to classify activities into four categories (Stand, Sit, Lay, Walk), with ten instances per class for evaluation' but does not specify the training, validation, or test dataset splits (e.g., percentages, sample counts, or cross-validation details). |
| Hardware Specification | No | The paper mentions using 'GPT-3.5' but does not provide any specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments or interacting with the LLM service. |
| Software Dependencies | No | The paper mentions the use of 'GPT-3.5' but does not provide specific version numbers for any software dependencies (e.g., programming languages, libraries, frameworks). |
| Experiment Setup | No | The paper describes the empirical demonstration and the dataset used, but it does not specify experimental setup details such as hyperparameters (e.g., learning rate, batch size, number of epochs) or specific training configurations. |