Amphibians are among the most threatened vertebrate groups globally, with more than 41% of species currently classified as threatened with extinction. Habitat destruction, climate change, emerging infectious diseases and unregulated exploitation contribute to their decline. Across Asia, exploitation for consumption, traditional medicine and the wildlife trade has been identified as a primary driver of amphibian population declines.

China has a long history of domestic and international amphibian trade, while the expansion of online commerce has changed how live animals are marketed and transported. Digital platforms such as Taobao and WeChat facilitate purchases without appropriate permits or scientific oversight, and amphibians are often listed under vague or incorrect trade names. Such mislabelling can undermine enforcement, distort records of species occurrences and trade volumes, and compromise conservation assessments and management decisions.

The four specimens were shipped as “ornamental amphibians” without a scientific name. Researchers photographed them after arrival and documented body colour, skin texture and limb proportions. The research was conducted under Institutional Animal Care and Use Committee approval number 2025028 from the ethics board of Nanjing Forestry University. Their snout–vent lengths were 95, 104, 101 and 97 mm.

For the genetic analysis, the researchers extracted genomic DNA from thigh muscle tissue. They amplified a 530-base-pair fragment of exon 1 of the nuclear tyrosinase gene, known as TYR, a marker used for identifying Asian dicroglossid frogs. After trimming and aligning the sequences with homologous records from the National Center for Biotechnology Information, the final dataset contained 572 base pairs from 51 sequences representing Q. spinosa and related species.

Phylogenetic relationships were estimated with Bayesian inference in MrBayes. The dataset was partitioned by codon position, and substitution models were selected with PartitionFinder. The Markov Chain Monte Carlo analysis used four chains over 10 million generations. Convergence checks found an average standard deviation of split frequencies below 0.05 and effective sample sizes above 200 for all parameters.

All four specimens produced high-quality TYR sequences that shared more than 99% identity with published Q. spinosa sequences. The Bayesian tree placed all four within the Q. spinosa clade with posterior probabilities greater than 0.99, supporting their identification as Chinese spiny frogs rather than H. chinensis. The analysis recovered seven well-supported clades corresponding to Fejervarya, Hoplobatrachus and five Quasipaa species.

Physical examination also supported the genetic result. Although the specimens had a general body shape similar to H. chinensis, they had relatively rough dorsal and lateral skin, chest tubercles with small round warts bearing tiny black spines, and pale-yellow ventral surfaces. Their throats were unmarked, while their limbs were either unmarked or had brown cloud-like spots. These traits are consistent with Q. spinosa, whose appearance overlaps with that of the widely farmed East Asian bullfrog.

The four-specimen case cannot establish the scale or origin of the trade, nor whether the misidentified frogs were legally traded, and the study did not test whether the commercial label was intentional. Nevertheless, the results show how visual identification can fail in commerce and why molecular verification may improve monitoring of traded amphibians. The authors propose integrating molecular diagnostics into customs inspections and online marketplace monitoring, expanding genetic reference libraries, and requiring clearer species labels. They also emphasize the livelihoods of communities traditionally involved in harvesting Q. spinosa and the need for public information on species identification and relevant wildlife-trade rules.

Subject of Research: Genetic identification of Quasipaa spinosa mislabelled as Hoplobatrachus chinensis in China’s online amphibian trade

Article Title: Hidden or inadvertent illegal amphibian trade? Genetic analyses reveal Quasipaa spinosa misidentified as Hoplobatrachus chinensis in the trade

Article References: Zhang, X., Borzée, A., Gill, S., & Othman, S. N. (2026). Hidden or inadvertent illegal amphibian trade? Genetic analyses reveal Quasipaa spinosa misidentified as Hoplobatrachus chinensis in the trade. Nature Conservation, 63, 247-257. https://doi.org/10.3897/natureconservation.63.183849

Image Credits: AI Generated

DOI: 10.3897/natureconservation.63.183849

Keywords: Quasipaa spinosa, Hoplobatrachus chinensis, amphibian trade, DNA barcoding, TYR gene, species misidentification, Taobao, wildlife commerce, biodiversity monitoring, Hidden, inadvertent, illegal

The core difficulty is that demand in live-streaming commerce is not a smooth, continuous curve that historical averages can capture. Each broadcast is a discrete, high-stakes event shaped by idiosyncratic factors: the charisma and reputation of the host, the specific assortment of products on offer, the timing of the session, and the unpredictable dynamics of viewer engagement. A misjudgment is punishing in both directions. Understock a session and the company loses sales in the very moment consumer excitement peaks, because viewers who cannot buy simply leave. Overstock it and capital sits idle in warehouses, tying up resources that a fast-moving retail operation cannot spare. Conventional forecasting methods, which typically extrapolate from past sales trends, struggle because the session itself, not the underlying trend, is the dominant driver of demand.

The researchers’ framework operates in two coupled stages. The first is session-based demand forecasting. Rather than treating each product’s sales history in isolation, the model blends historical transaction data with engagement-proxy features, signals that stand in for the human and contextual elements of a live broadcast, such as expected viewer activity and session characteristics. The goal is to predict total demand for each product within a given live-streaming event before that event takes place, giving the supply chain a forward-looking estimate it can act on during the crucial pre-session planning window.

To build and test this forecasting engine, the team constructed a synthetic dataset of 500 live-streaming sessions derived from two well-known public sources: the User Behavior Data from Taobao, which captures real shopping activity from one of the world’s largest e-commerce platforms, and the Twitch Live-Streaming Interactions Sample Dataset, which documents how audiences behave during live video streams. By combining these sources through probabilistic models, the researchers created a multi-dimensional simulation of a live-streaming e-commerce ecosystem that is statistically grounded in real-world behavior while remaining controllable for experimentation. Notably, the pipeline explicitly simulates the zero-demand phenomenon, the common but frequently overlooked situation in which a product sells nothing at all during a session, a challenge that public datasets rarely represent and that can badly distort models trained without it.

The forecasting results highlight a finding that echoes a broader trend in applied machine learning: on tabular data, carefully tuned gradient boosting often beats deep learning. The team compared multiple model families and found that an arithmetic-mean ensemble of ten independently trained Gradient Boosting Machines delivered the highest accuracy, achieving a mean R-squared of 0.9364 across 20 independent runs, along with the lowest standard deviation of any approach tested. That combination of high accuracy and low variance matters enormously in an operational setting, where a forecasting engine that performs brilliantly one week and poorly the next is nearly as damaging as one that is consistently mediocre. The ensemble’s stability suggests it can be trusted to feed downstream decisions reliably.

The second stage of the framework is where the work becomes genuinely distinctive. Accurate forecasts alone do not move boxes; someone or something must decide how much inventory to pull from a central supply and position for each session. The researchers automated this orchestration with a tabular Q-learning agent, a classic reinforcement learning algorithm that learns optimal ordering policies directly from sequences of demand. The agent operates in an environment where every decision carries a cost: holding inventory incurs carrying costs, running out triggers stockout penalties, and placing orders costs money. By repeatedly simulating allocation decisions and observing the resulting rewards, the agent converges on a policy that dynamically balances these competing pressures without any hand-tuned rules.

The training dynamics of the Q-learning agent are instructive. The agent converged within approximately 900 episodes, a remarkably small number by reinforcement learning standards, and achieved a 93.3 percent fill rate, meaning it successfully met demand in nearly every simulated scenario while keeping the trade-off between holding, stockout, and ordering costs in check. This efficiency stems partly from the tabular formulation, which is well suited to the discrete, session-by-session structure of the problem. Each live-streaming event becomes a decision point, and the agent’s accumulated experience across sessions teaches it when to stock aggressively, when to hold back, and how to hedge against the uncertainty that even the best forecast cannot eliminate.

The methodological contribution, the authors argue, is the integration itself: a session-aware framework that couples ensemble forecasting with reinforcement learning-driven orchestration in a supply chain context designed specifically for live-streaming commerce. Most prior work has treated demand prediction and inventory optimization as separate problems, solved by separate teams with separate tools. By binding them together, the framework ensures that the uncertainty captured by the forecaster is directly consumed by the orchestrator, so that allocation decisions reflect not just a point estimate of demand but the operational realities of cost and availability. The result is a pipeline that can, in principle, run automatically: data flows in, forecasts are generated, and stock is positioned, all before a host says a single word on camera.

The practical implications extend well beyond the platforms where live-stream selling originated. What began as a Chinese e-commerce phenomenon has spread rapidly across Southeast Asia, and Western retailers are increasingly experimenting with shoppable video formats on social platforms. Every one of these operations faces the same pre-session allocation dilemma, and the framework’s reliance on publicly available behavioral data means the approach is reproducible without proprietary access. The explicit modeling of zero-demand sessions is particularly valuable for smaller sellers, whose product catalogs often include items that simply fail to sell in a given broadcast, and whose forecasting systems are frequently blindsided by exactly those cases.

There are, of course, caveats. The forecasting engine was validated on a synthetic dataset, however realistically constructed, and real-world deployment would require adaptation to platform-specific behaviors, promotional dynamics, and shifting audience tastes. The Q-learning agent’s tabular structure, while efficient, may need scaling strategies as the number of products and sessions grows. Yet the study demonstrates that the pieces of an automated, intelligent inventory system for live-streaming commerce can be assembled from proven, well-understood machine learning components, and that doing so yields measurable gains in both predictive accuracy and operational performance. As live-streaming continues to compress the distance between marketing and fulfillment, research like this points toward supply chains that are no longer reactive afterthoughts but active participants in the show itself, quietly ensuring that when the audience rushes to buy, the products are already waiting.

Subject of Research: Machine learning-based session-level demand forecasting and reinforcement learning inventory allocation for live-streaming e-commerce supply chains

Article Title: Discovering session-level demand patterns for reinforcement learning-based dynamic inventory allocation in live-streaming e-commerce

Article References: Ho, T.-L., Pham, H., Hoang, Q. D., Binh, A. D. T., Lam, T.-P., Ngo, D.-T., & Nguyen, T. T. (2026). Discovering session-level demand patterns for reinforcement learning-based dynamic inventory allocation in live-streaming e-commerce. Knowledge and Information Systems, 68(1), Article 278. https://doi.org/10.1007/s10115-026-02895-y

Image Credits: AI Generated

DOI: 10.1007/s10115-026-02895-y

Keywords: live-streaming e-commerce, demand forecasting, reinforcement learning, Q-learning, gradient boosting, inventory optimization, supply chain management, session-based prediction, machine learning, Taobao, Twitch, ensemble learning