Accounting Graph Transformer for Short-History Multi-KPI Forecasting in Small Businesses

• URL: http://arxiv.org/abs/2608.07037v1
• Date: Fri, 07 Aug 2026 09:47:44 GMT
• Title: Accounting Graph Transformer for Short-History Multi-KPI Forecasting in Small Businesses
• Abstract summary: We study joint 12-month forecasting of 13 income-statement, balance-sheet, cash-flow, and working-capital key performance indicators from 71 monthly ledger series.<n>Across 11,993 forecast origins from 1,060 unseen companies, AGT achieves sample-macro mean absolute error (MAE) $0.6990 pm 0.0013$ over three independent seeds.<n>AGT is best matched on all 13 against LightGBM, TimeMixer, and SOFTS in the seed-42 comparison.
• Score: 1.3750624267664158
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Small businesses often have only 12-24 months of accounting history, yet planning and risk workflows require coordinated forecasts across financial statements. We study joint 12-month forecasting of 13 income-statement, balance-sheet, cash-flow, and working-capital key performance indicators (KPIs) from 71 monthly ledger series. We introduce the Accounting Graph Transformer (AGT), which represents each ledger series as a masked token, exchanges information through typed attention on a fixed accounting-relation graph, pools target-specific context, and fuses it with a gated three-month recency path. Across 11,993 forecast origins from 1,060 unseen companies, AGT achieves sample-weighted KPI-macro mean absolute error (MAE) $0.6990 \pm 0.0013$ over three independent seeds, compared with $0.7378 \pm 0.0014$ for the strongest baseline, LightGBM. At the pre-specified seed 42, a paired company-clustered bootstrap gives a LightGBM-minus-AGT difference of 0.0395 with 95% confidence interval (CI) $[0.0350,0.0439]$. AGT is best on all 13 KPIs against LightGBM, TimeMixer, and SOFTS in the matched seed-42 comparison, while final-architecture ablations show that relational attention, accounting topology, and the recency path each improve validation and test accuracy. On 7,094 additional unseen companies with origins sampled from January-May 2025, AGT obtains 0.7548 MAE versus 0.7694 for SOFTS. A single 5.3M-parameter model produces 156 aligned forecasts without company-specific fitting, providing one forecasting layer for integrated planning, liquidity, and working-capital analysis.

Related papers

• A time-series classification framework for individual-level absenteeism prediction under severe class imbalance [0.0]
  Staff absenteeism imposes substantial operational costs in high-demand work environments.<n>We propose a Time Series Classification framework that separates historical attendance sequences from future absence labels.
  arXiv  Detail & Related papers  (2026-06-30T11:44:52Z)
• MacroLens: A Multi-Task Benchmark for Contextual Financial Reasoning under Macroeconomic Scenarios [44.59910717749994]
  MacroLens covers 4,416 U.S. small-cap splits and micro-cap gradient splits.<n>Seven tasks share one point-in-time panel of prices, 46.8M equities over accounting facts, 53 macroeconomic series, 295,860 SEC filings, and 215,882 news articles.<n>Tasks span contextual forecasting, public and private valuation, statement generation from fundamentals and descriptions, scenario-conditioned returns, and real-estate valuation.
  arXiv  Detail & Related papers  (2026-06-23T07:52:44Z)
• RAVEN: A Regime-Aware Variable-context Expert Network for Financial Time Series Forecasting [83.06074370551887]
  A fixed context window is mismatched to the time-varying optimal look-back of non-stationary price processes.<n>We propose a Mixture-of-Experts framework designed to adaptively determine the temporal context for each input sample.<n> Experiments on cumulative log-return prediction (HS300, S&P500) and fund sales forecasting demonstrate that RAVEN achieves SOTA performances, improves Pearson correlation by 9.2% on HS300 and 20.2% on S&P500, and reduces MSE by 18.2% on fund sales forecasting.
  arXiv  Detail & Related papers  (2026-06-23T02:11:04Z)
• ATLAS: All-round Testing of Long-context Abilities across Scales [42.83200405769639]
  ATLAS is a benchmarking framework that redefines long-context evaluation as length-dependent capability profiling.<n> ATLAS contributes three methodological principles: (i) a layered taxonomy separating foundational operations from application workloads so failures can be attributed, (ii) length-aware AUC scoring that integrates score-length curves over a fixed 8K-1M grid, replacing single-point metrics with full degradation profiles, and (iii) ATLAScore, a harmonic-mean aggregate over taxonomy categories that penalizes imbalanced profiles.
  arXiv  Detail & Related papers  (2026-05-27T07:33:47Z)
• SAGA: A Sequence-Adaptive Generative Architecture for Multi-Horizon Probabilistic Forecasting with Adaptive Temporal Conformal Prediction [0.0]
  We propose SAGA, a decoder-only transformer that delivers individual-level prediction intervals with finite-sample marginal coverage guarantees.<n>We trained on the longitudinal Swedish LISA register over 1990 to 2022, comprising 2,143,817 individuals and 61,284,903 person-years.<n> SAGA reduces continuous ranked probability score by 31.9 percent at the ten-year horizon and mean absolute error by 37.7 percent at the twenty-year horizon.
  arXiv  Detail & Related papers  (2026-05-18T18:35:20Z)
• Shapley Value-Guided Adaptive Ensemble Learning for Explainable Financial Fraud Detection with U.S. Regulatory Compliance Validation [0.34376560669160394]
  Financial crime costs U.S. institutions over $32 billion each year.<n>Many AI tools for fraud detection operate as black boxes that cannot provide transparent, auditable explanations.<n>This study offers a thorough evaluation of explanation quality across faithfulness and stability.
  arXiv  Detail & Related papers  (2026-04-14T19:00:20Z)
• Detecting High-Potential SMEs with Heterogeneous Graph Neural Networks [0.0]
  Small and Medium Enterprises (SMEs) constitute 99.9% of U.S. businesses and generate 44% of economic activity.<n>We introduce SME-HGT, a Heterogeneous Graph Transformer framework that predicts which Phase I awardees will advance to Phase II funding using exclusively public data.
  arXiv  Detail & Related papers  (2026-02-23T08:35:55Z)
• Phase Transition for Budgeted Multi-Agent Synergy [41.486076708302456]
  Multi-agent systems can improve reliability, yet under a fixed inference budget they often help, saturate, or even collapse.<n>We develop a minimal and calibratable theory that predicts these regimes from three binding constraints of modern agent stacks.
  arXiv  Detail & Related papers  (2026-01-24T05:32:50Z)
• LLM Output Drift: Cross-Provider Validation & Mitigation for Financial Workflows [0.5798758080057375]
  Nondeterministic outputs (output drift) undermine auditability and trust.<n>We quantify drift across five model architectures on regulated financial tasks.<n>This finding challenges conventional assumptions that larger models are universally superior for production deployment.
  arXiv  Detail & Related papers  (2025-11-10T19:54:00Z)
• A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning [40.6234318894435]
  Large language models split into two families: reasoning-centric LLMs and agentic LLMs.<n>This divide arises from fundamentally different training objectives, leading to mismatched strengths and inefficiency on simple queries.<n>We present Adaptive Agent Foundation Model (A$2$FM), a unified framework that follows a route-then-align principle.
  arXiv  Detail & Related papers  (2025-10-13T17:08:25Z)
• Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation [43.29267000439331]
  Large language models (LLMs) have demonstrated impressive reasoning capabilities when provided with chain-of-thought exemplars.<n>In this work, we introduce Prompting Test-Time Scaling (P-TTS), a simple yet effective inference-time data augmentation strategy.
  arXiv  Detail & Related papers  (2025-10-10T17:57:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.