SEQUENTIAL OPTIMIZATION OF REAL-TIME REVENUE USING ADAPTIVE ONLINE LEARNING

Revenue optimization represents a major strategic challenge for large-scale companies and e commerce platforms.In environments characterized by massive and heterogeneous user populations, the real - time adaptation of marketing strategies becomes a critical driver of performance. This paper proposes an adaptive intelligent algorithm based on online learning to maximize revenue generated through premium subscription plans within a platform serving millions of users. The problem is formulated as a sequential decision-making process under uncertainty. Nine distinct marketing strategies, differentiated by promotional offers and commercial incentives, are dynamically presented to users during their navigation sessions. No prior knowledge of conversion rates is assumed, and each user interaction produces binary feedback corresponding to success or failure. The objective is to rapidly identify the strategy yielding the highest conversion rate while minimizing exploration costs. Experimental results demonstrate that the Thompson Sampling based algorithm outperforms both random selection and Upper Confidence Bound (UCB) approaches in identifying the optimal strategy. After only a limited number of interactions, the proposed method efficiently detects the most profitable strategy, thereby reducing advertising and operational costs.

Authors

Institutions

Publication Details

Journal
International Journal of Advanced Research
Published
2026-11-18
DOI
https://doi.org/10.21474/ijar01/24520
Primary Topic
Advanced Bandit Algorithms Research
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

SEQUENTIAL OPTIMIZATION OF REAL-TIME REVENUE USING ADAPTIVE ONLINE LEARNING

Mouale Ndah M. Bienvenue, Dalie Luc-Donald, Tape Jean Max Habib
International Journal of Advanced Research
Advanced Bandit Algorithms Research
article

SEQUENTIAL OPTIMIZATION OF REAL-TIME REVENUE USING ADAPTIVE ONLINE LEARNING

Mouale Ndah M. Bienvenue, Dalie Luc-Donald, Tape Jean Max Habib
article en

Abstract

Revenue optimization represents a major strategic challenge for large-scale companies and e commerce platforms.In environments characterized by massive and heterogeneous user populations, the real - time adaptation of marketing strategies becomes a critical driver of performance. This paper proposes an adaptive intelligent algorithm based on online learning to maximize revenue generated through premium subscription plans within a platform serving millions of users. The problem is formulated as a sequential decision-making process under uncertainty. Nine distinct marketing strategies, differentiated by promotional offers and commercial incentives, are dynamically presented to users during their navigation sessions. No prior knowledge of conversion rates is assumed, and each user interaction produces binary feedback corresponding to success or failure. The objective is to rapidly identify the strategy yielding the highest conversion rate while minimizing exploration costs. Experimental results demonstrate that the Thompson Sampling based algorithm outperforms both random selection and Upper Confidence Bound (UCB) approaches in identifying the optimal strategy. After only a limited number of interactions, the proposed method efficiently detects the most profitable strategy, thereby reducing advertising and operational costs.

International Journal of Advanced ResearchVol. 14(11)
Université Nangui Abrogoua (CI), Université Pelefero Gon Coulibaly (CI)
Advanced Bandit Algorithms Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon