AI Research

Making Alternative Data Work: Context-Augmented LLM... | AI Research

Key Takeaways

Making Alternative Data Work: Context-Augmented LLMs for Financial Forecasting This paper explores how to better use "alternative data"—non-traditional infor...
These signals may reveal information that is not captured by traditional public sources and can therefore provide complementary information for forecasting firms' future financial performance.
Meanwhile, large language models (LLMs) can interpret instructions, learn from in-context examples, and generate predictions by combining heterogeneous information without task-specific parameter updates.
Motivated by this potential flexibility, we investigate whether an LLM can forecast firm performance by integrating alternative data with other financial information through in-context learning.
We propose a two-agent framework that first identifies the firms for which each alternative data channel is likely to be informative and then predicts revenue using firm- and channel-specific context.

Paper AbstractExpand

When forecasting a firm's future financial performance, alternative data - data collected from non-traditional sources such as consumer transactions, web traffic, and prediction markets - can provide timely signals about firms' operating activities and broader market conditions. These signals may reveal information that is not captured by traditional public sources and can therefore provide complementary information for forecasting firms' future financial performance. However, firm-level alternative data often have limited historical coverage, are relevant only to specific prediction targets or subsets of firms, and are distributed across numerous heterogeneous channels, making them difficult to incorporate flexibly into conventional forecasting approaches. Meanwhile, large language models (LLMs) can interpret instructions, learn from in-context examples, and generate predictions by combining heterogeneous information without task-specific parameter updates. Motivated by this potential flexibility, we investigate whether an LLM can forecast firm performance by integrating alternative data with other financial information through in-context learning. We propose a two-agent framework that first identifies the firms for which each alternative data channel is likely to be informative and then predicts revenue using firm- and channel-specific context. We evaluate the framework across four commercial alternative data channels. In our experiments, adding alternative data in context alongside other financial information improves the LLM's forecasting relative to either source alone, and these forecasts are more accurate than those of standard forecasting baselines. These findings suggest that LLMs provide a flexible and practical approach to integrating alternative data with heterogeneous financial information.

Making Alternative Data Work: Context-Augmented LLMs for Financial Forecasting
This paper explores how to better use "alternative data"—non-traditional information like web traffic, credit card spending, foot traffic, and prediction markets—to forecast a company’s future financial performance. While this data can provide timely signals about a firm's health, it is often difficult to use because it is fragmented, limited in history, and only relevant to specific types of businesses. The authors propose using Large Language Models (LLMs) to integrate this diverse information through "in-context learning," allowing the model to make predictions without needing to be retrained for every specific data source or company. The same large language models question is explored in Trace2Tower, which adds a research perspective.

A Two-Agent Framework

To handle the complexity of different data types, the researchers developed a two-agent system. First, a "screening agent" evaluates whether a specific alternative data channel is actually relevant to a company’s business model. For example, it might decide that web traffic is a strong indicator for an e-commerce company but less useful for a brick-and-mortar retailer. Second, a "prediction agent" combines this filtered alternative data with the company’s historical financial records and earnings call transcripts. Because some alternative data may be proprietary or unfamiliar to the LLM, the agent is equipped with search tools to retrieve background information, ensuring it can correctly interpret the data in the context of the firm’s operations.

Improving Forecast Accuracy

The study evaluated this framework across four commercial data channels: card spending, web traffic, foot traffic, and KPI prediction markets. The results show that incorporating alternative data alongside traditional financial information consistently leads to more accurate revenue forecasts than using either source alone. Furthermore, the LLM-based approach outperformed standard statistical forecasting baselines and, in a majority of cases, proved more accurate than the consensus forecasts provided by financial analysts. The same ai evaluation question is explored in STAIR (STructure Aware Information Retriever), which adds a research perspective.

Why This Matters

The primary advantage of this approach is its flexibility. Traditional forecasting models often require significant, specialized training for every new data source, which is costly and time-consuming. By using an LLM’s ability to learn from context, this framework can incorporate new, heterogeneous data sources immediately without requiring task-specific parameter updates. This suggests that LLMs offer a practical, scalable way to bridge the gap between raw, non-traditional data and actionable financial insights. The same ai evaluation question is explored in Beyond Aggregate Scores, which adds a research perspective. as detailed in the full paper on Arxiv

Comments (0)

No comments yet

Be the first to share your thoughts!