English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Training models on data obtained from randomized experiments is ideal formaking good decisions. However, randomized experiments are oftentime-consuming, expensive, risky, infeasible or unethical to perform, leavingdecision makers little choice but to rely on observational data collected underhistorical policies when training models. This opens questions regarding notonly which decision-making policies would perform best in practice, but alsoregarding the impact of different data collection protocols on the performanceof various policies trained on the data, or the robustness of policyperformance with respect to changes in problem characteristics such as action-or reward- specific delays in observing outcomes. We aim to answer suchquestions for the problem of optimizing sales channel allocations at LinkedIn,where sales accounts (leads) need to be allocated to one of three channels,with the goal of maximizing the number of successful conversions over a periodof time. A key problem feature constitutes the presence of stochastic delays inobserving allocation outcomes, whose distribution is both channel- and outcome-dependent. We built a discrete-time simulation that can handle our problemfeatures and used it to evaluate: a) a historical rule-based policy; b) asupervised machine learning policy (XGBoost); and c) multi-armed bandit (MAB)policies, under different scenarios involving: i) data collection used fortraining (observational vs randomized); ii) lead conversion scenarios; iii)delay distributions. Our simulation results indicate that LinUCB, a simple MABpolicy, consistently outperforms the other policies, achieving a 18-47% liftrelative to a rule-based policy

Sales Channel Optimization via Simulations Based on Observational Data with Delayed Rewards: A Case Study at LinkedIn