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

Reinforcement learning has become one of the best approach to train acomputer game emulator capable of human level performance. In a reinforcementlearning approach, an optimal value function is learned across a set ofactions, or decisions, that leads to a set of states giving different rewards,with the objective to maximize the overall reward. A policy assigns to eachstate-action pairs an expected return. We call an optimal policy a policy forwhich the value function is optimal. QLBS, Q-Learner in theBlack-Scholes(-Merton) Worlds, applies the reinforcement learning concepts, andnoticeably, the popular Q-learning algorithm, to the financial stochastic modelof Black, Scholes and Merton. It is, however, specifically optimized for thegeometric Brownian motion and the vanilla options. Its range of application is,therefore, limited to vanilla option pricing within financial markets. Wepropose MQLV, Modified Q-Learner for the Vasicek model, a new reinforcementlearning approach that determines the optimal policy of money management basedon the aggregated financial transactions of the clients. It unlocks newfrontiers to establish personalized credit card limits or to fulfill bank loanapplications, targeting the retail banking industry. MQLV extends thesimulation to mean reverting stochastic diffusion processes and it uses adigital function, a Heaviside step function expressed in its discrete form, toestimate the probability of a future event such as a payment default. In ourexperiments, we first show the similarities between a set of historicalfinancial transactions and Vasicek generated transactions and, then, weunderline the potential of MQLV on generated Monte Carlo simulations. Finally,MQLV is the first Q-learning Vasicek-based methodology addressing transparentdecision making processes in retail banking.

MQLV: Optimal Policy of Money Management in Retail Banking with Q-Learning