Otto Group (Germany)

This work introduces TRON, a scalable session-based Transformer Recommender using Optimized Negative-sampling. Motivated by the scalability and performance limitations of prevailing models such as SASRec and GRU4Rec + , TRON integrates top-k negative sampling and listwise loss functions to enhance its recommendation accuracy. Evaluations on relevant large-scale e-commerce datasets show that TRON improves upon the recommendation quality of current methods while maintaining training speeds similar to SAS-Rec. A live A/B test yielded an 18.14% increase in click-through rate over SASRec, highlighting the potential of TRON in practical settings. For further research, we provide access to our source code 1 and an anonymized dataset 2 . • Applied computing → Online shopping; • Information systems → Recommender systems; • Computing methodologies → Neural networks.

Private equity shareholder agreements are essential to the successful relationship between venture capital (VC) providers and recipients and are structured to balance the interests and objectives of both parties. However, these contracts are complex and contain a broad range of design options. The authors propose a model to classify early-cycle companies into four groups according to two dimensions: bargaining power and development state. Their survey of VC providers suggests most VC contracts include a core set of standardized investor rights. Additionally, there are varying rights according to the degree of bargaining power and development state, preserving contract flexibility to accommodate a range of investment prospects.