Company aware model improves quarter ahead revenue forecasting accuracy
CAME: Company-Aware Evidence-Memory Experts for Interpretable Quarter-Ahead Revenue Forecasting
Computation and LanguageMachine Learning
Summary
Quarter-ahead revenue forecasts are tricky because they need to be numerically precise and timely, while also explaining factors behind the numbers for specific companies. The authors developed a system called CAME that combines stable historical data with recent company news and error trends to make more accurate revenue predictions. Their tests on 12 big tech companies showed CAME performed better than previous methods. It also provides explanations tying forecast changes back to specific evidence, helping users understand and trust the predictions.
What this means in practice
- •For financial analysts: Produce more accurate and interpretable revenue forecasts for public tech companies using current financial narratives and historical trends.
- •For investment management teams: Improve investment decisions by integrating a company-aware forecasting tool that links revenue predictions with underlying textual evidence from reports.
Authors
Ya-Wen Wu, Meng-Fen Chiang, Kuang-Da Wang, Wen-Chih Peng
Abstract
Quarter-ahead revenue forecasting requires company-scale numerical accuracy, strict temporal validity, and company-specific interpretation of narrative disclosures. LLMs can distill textual evidence but can produce scale-misaligned forecasts, whereas history-based anchors are stable but miss forecast-time signals such as product transitions, supply constraints, and management guidance. We introduce CAME (Company-Aware Evidence-Memory Experts), a residual-forecasting framework that refines a no-leakage statistical anchor when current semantic evidence and prior error patterns justify an adjustment. On a development-inclusive rolling backtest of 336 company-quarters from 12 large public technology and platform firms, CAME achieves the lowest aggregate point-estimate error among the reported methods, with statistically supported macro-sMAPE gains over the matched Statistical Anchor, and outperforms History + Guidance on all six aggregate metrics. CAME also links adjustments to source-linked evidence cards and guarded memory traces, supporting forecast inspection, provenance, and failure localization.