Forecasting Sales Delay through Time-aware Analysis of Sales Events in Textual Reports

Masaya Tsunokake, Yuta Koreeda, Yuhei Niwa, Terufumi Morishita, Teppei Inoue, Hiroaki Ozaki, Yasuhiro SogawaarXiv 2026 · arXiv

In the world of B2B manufacturing and software, timing is everything. Companies often operate on a "make-to-order" strategy, reserving expensive resources—engineers, factory floor time, and raw materials—based on a scheduled order date. But what happens when a client drags their feet? A delay doesn't just push back a deadline; it leaves reserved resources idling, driving up costs and disrupting entire pipelines.

A new paper from researchers at Hitachi, Ltd., titled "Forecasting Sales Delay through Time-aware Analysis of Sales Events in Textual Reports," introduces a novel way to predict these delays by reading between the lines of sales representatives' reports.

TL;DR

The researchers introduce sales delay forecasting, a task that predicts the gap between a scheduled and actual order date using NLP. By extracting "confidence" and "status" features from textual sales reports, their method achieved a 16% lower Mean Absolute Error (MAE) than traditional project-info baselines and outperformed state-of-the-art Large Language Models (LLMs) like Qwen3.

What Problem Does This Paper Address?

In B2B sales, the "scheduled order date" is often an estimate made early in the process. However, the actual order date ($d_{actual}$) is a moving target influenced by the client’s internal consensus-building and willingness to commit.

Unlike software development or construction, where progress can be measured by physical artifacts (like lines of code or bricks laid), sales progress is largely invisible and highly subjective. Current forecasting methods often rely on static project data (like budget or initial duration), which fails to capture the evolving "vibe" of a deal. The authors argue that the most valuable data lies in the textual reports written by sales reps after client meetings, but this data is unstructured and difficult to quantify.

Figure 1: Sales delay forecasting. We address this task of fore- casting delay days (𝑦𝑡) from scheduled order date utilizing sales data at time 𝑡.

Methods

The authors propose a three-step pipeline to turn messy text into a precise delay forecast:

  1. Analysis of Textual Reports: The system uses NLP tools (like spaCy and GiNZA) to extract date expressions and keywords. It maps these to four typical sales phases: Contact, Proposal, Negotiation, and Closing. Crucially, it distinguishes between Facts (past events) and Prospects (future events mentioned by the rep).
  2. Feature Creation: The core innovation lies in two types of features:
  3. Confidence Features: These act as a proxy for the client's willingness to order. For example, if a rep writes about a "Closing" event that is significantly later than the scheduled date, the model flags low confidence. It also incorporates sentiment analysis to gauge the rep's optimism.
  4. Status Features: These provide an objective reality check. They track the current phase of the deal, how long the deal has been stuck in that phase, and how many days remain until the scheduled deadline.
  5. Regression Model: These features are fed into a Support Vector Machine (SVM) with an RBF kernel to predict the final delay ($y_t$).
Figure 2: Overview of our method. Our method first extracts sales events from textual reports by identifying date expressions and keywords tied with sales phases, and then distinguishes whether the events refer to the future or the past. Example extracted events are shown in the top of this figure. Next, our method creates confidence and status features based on the extracted events. Confidence features represent sales reps’ confidence and are created through utilizing the extracted future events (#Conf.1) and sentiments detected from textual reports (#Conf.2). Status features objectively describe sales process status. Status features are created through utilizing remaining days until the scheduled order date (#Stat.3) and the extracted past events that determine the current phase (#Stat.1) and days since the current phase started (#Stat.2).

Datasets

The study used a proprietary dataset of real-world sales data from a Japanese company.

  • Scope: Closed sales projects with multiple forecasting points ($t$) as new reports were added.
  • Size: The final evaluation used 1,242 instances for training, 245 for development, and 315 for testing.
  • Baselines: The model was compared against trivial baselines (Mean/Zero), a feature-based baseline using only project metadata (ProjectInfo), and several LLMs (RoBERTa, LUKE, BigBird, and Qwen3).

Key Insights and Ideas

  • LLMs Aren't Always the Answer: Interestingly, fine-tuned LLMs like RoBERTa and even powerful few-shot models like Qwen3-32B struggled with this task. They tended to predict values close to the mean, failing to capture the wide distribution of actual delays. Explicitly engineering features from the text proved far more effective than letting a model "read" the whole report.
  • The "Reality Check" Matters: Sales reps are human and prone to bias. The researchers found that combining Confidence (the rep's subjective view) with Status (the objective timeline) was essential. An optimistic rep reporting from the "Contact" phase just days before a deadline is a major red flag that the model can now catch.
  • Time-Awareness is Crucial: The model's accuracy improves significantly as the actual order date approaches. By capturing the "rate of change" in prospects and status, the model becomes a better indicator of reality over time.
Table 1: Our features. Confidence features represent sales reps’ confidence. Status features describe sales process status to consider whether the confidence objectively looks reasonable.

Key Results

  • Superior Accuracy: The proposed method achieved an MAE of 70.80, a 16% improvement over the ProjectInfo baseline (84.06) and significantly better than the best LLM baseline (Qwen3-32B at 76.10).
  • Ablation Success: Removing the "Prospect" feature (anticipated future dates) caused the MAE to jump by +44.17, proving that the rep's future expectations are the single most important signal in the text.
  • LLM "Thinking" Helps: For the LLM baselines, enabling Qwen3’s "thinking mode" (Chain-of-Thought) improved performance, as the model attempted to perform arithmetic on the dates mentioned in the text—though it still couldn't beat the specialized feature-based approach.
MAE performance over time. The model becomes much more accurate (lower MAE) as the deal nears completion (moving left on the x-axis).

Limitations and Future Work

  • Language Specificity: The current implementation is tailored to Japanese text and specific Japanese sales terminology. While the framework is general, the keyword extractors would need to be rebuilt for other languages.
  • Report Quality: The model relies entirely on sales reps writing detailed, honest reports. If a rep is lazy or intentionally misleading in their documentation, the model's "Confidence" features will suffer.
  • Inference Speed: While the feature-based model is fast, the researchers noted that using LLMs with "thinking modes" for comparison requires substantially more inference time, making them less practical for real-time enterprise dashboards.

Future work could involve integrating this with resource management systems to automatically trigger alerts when a high-value project is likely to slip.

Summary updated

Abstract

Business-to-business (B2B) companies develop and deliver a one-of-a-kind product in response to a client's orders. To prepare resources for development beforehand, companies estimate dates when they will receive orders from clients in their sales process, called scheduled order dates. However, dates when the companies actually receive orders can differ from the scheduled order dates. This difference increases costs in the development. If the difference could be forecasted before receiving orders, companies could optimize their resource preparation. Towards reducing the costs, we introduce sales delay forecasting, a novel task of forecasting delay days from the scheduled order dates during sales process where sales representatives (sales reps) interact with the clients to receive orders. Sales delay forecasting is challenging because the sales process progress inherently involves uncertainty and depends on the client's willingness to order. To address this task, we propose confidence features which represent sales reps' confidence as a proxy measure of the client's willingness to order. To represent it, our method extracts dates of future sales events anticipated by sales reps from textual reports. To consider whether the confidence objectively looks reasonable, we also introduce status features which describe sales process status based on current date and past events. In experiments using real sales data, our method achieved a 16% lower mean absolute error compared with a feature-based baseline similar to a prior work. Moreover, our method outperformed non-feature-based baselines using large language models, indicating that it is crucial to explicitly create our features.
BibTeX
@misc{tsunokake2026forecasting,
  author = {Masaya Tsunokake and Yuta Koreeda and Yuhei Niwa and Terufumi Morishita and Teppei Inoue and Hiroaki Ozaki and Yasuhiro Sogawa},
  title = {{Forecasting Sales Delay through Time-aware Analysis of Sales Events in Textual Reports}},
  year = {2026},
  eprint = {2611.16704},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.16704},
}
Figure