Can ChatGPT predict the future? Training AI to figure out what happens next


NYU’s LLMtime program finds the next likely event in a sequence of events, as represented in strings of numeric digits.

New York University

Today’s generative artificial intelligence programs, tools such as ChatGPT, are on course to produce many more kinds of results than just text, as ZDNET has explored in some depth. 

One of the most important of those “modalities,” as they’re known, is what’s called time series data — data that measures the same variables at different points in time to spot trends. Data in a time series format can be important for things such as tracking patient medical history over time with the entries made by a physician in a chart. Doing what’s called time series forecasting means taking the historical data and predicting what’s happening next; for example: “Will this patient get better?”

Also: ChatGPT seems to be confused about when its knowledge ends

Traditional approaches to time series data involve software specially designed for just that type of data. But now, generative AI is gaining a new ability to handle time series data in the same way it handles essay questions, image generation, software coding, and the various other tasks at which ChatGPT and similar programs have excelled. 

In a new study published this month by Nate Gruver of New York University and colleagues from NYU and Carnegie Mellon, OpenAI’s GPT-3 program is trained to predict the next event in a time series similar to predicting the next word in a sentence. 

“Because language models are built to represent complex probability distributions over sequences, they are theoretically well-suited for time series modeling,” write Gruver and team in their paper, “Large Language Models Are Zero-Shot Time Series Forecasters,” posted on the arXiv pre-print server. “Time series data typically takes the exact same form as language modeling data, as a collection of sequences.”

The program they created, LLMTime, is “exceedingly simple,” write Gruver and team, and able to “exceed or match purpose-built time series methods over a range of different problems in a zero-shot fashion, meaning that LLMTime can be used without any fine-tuning on the downstream data used by other models.”

Also: Generative AI will far surpass what ChatGPT can do. Here’s everything on how the tech advances

The key to building LLMTime was for Gruver and team to re-think what’s called “tokenization,”…