12 Dyna-SPECTS: DYNAmic enSemble of Price Elasticity Computation models using Thompson Sampling in e-commerce
-
Srividhya Sethuraman
Abstract
This work introduces Dyna-SPECTS, a novel dynamic ensemble-based Thompson sampling model for calculating price elasticity (PE) in the e-commerce sector, focusing on kids’ clothing. The model uniquely amalgamates four distinct Thompson sampling based algorithms namely - algorithms - distribution approximation, XGBoost regressor, GAN, and MCMC sampling - to determine PE distribution parameters. Dyna-SPECTS’s outstanding feature is its dynamic ensemble mechanism, which adeptly selects optimal PE values from a suite of strategies like minimum, maximum, average, weighted MAPE, and linear regressor, guided by cumulative rewards. This approach adapts to variable market conditions in the constantly evolving e-commerce landscape, including competitor pricing, seasonal changes, and customer segmentation. Empirical tests across diverse datasets have confirmed Dyna-SPECTS’s exceptional performance, showcasing substantial improvements in sales and margins, especially for SKUs experiencing PE fluctuations. The model also demonstrates efficacy in using transfer learning for PE computation, yielding a 7% margin improvement and a remarkable 35.3% reduction in RMSE for demand forecasts. Innovations in Cross-PE coefficient integration and price personalization have led to further margin enhancements. Moreover, the model excels in omnichannel pricing, achieving a 17.5% margin increase. Long-tailed product pricing using these PE values showed an increase in sales volume and revenue compared to traditional pricing strategies. Dyna-SPECTS prioritizes scalability using parallelization, distributed computing, and optimizing algorithms, efficiently managing a high volume of SKUs without compromising computational effectiveness and achieving rapid convergence. It represents a significant leap in dynamic price elasticity computation, offering a scalable, versatile, and empirically proven solution for e-commerce pricing challenges.
Abstract
This work introduces Dyna-SPECTS, a novel dynamic ensemble-based Thompson sampling model for calculating price elasticity (PE) in the e-commerce sector, focusing on kids’ clothing. The model uniquely amalgamates four distinct Thompson sampling based algorithms namely - algorithms - distribution approximation, XGBoost regressor, GAN, and MCMC sampling - to determine PE distribution parameters. Dyna-SPECTS’s outstanding feature is its dynamic ensemble mechanism, which adeptly selects optimal PE values from a suite of strategies like minimum, maximum, average, weighted MAPE, and linear regressor, guided by cumulative rewards. This approach adapts to variable market conditions in the constantly evolving e-commerce landscape, including competitor pricing, seasonal changes, and customer segmentation. Empirical tests across diverse datasets have confirmed Dyna-SPECTS’s exceptional performance, showcasing substantial improvements in sales and margins, especially for SKUs experiencing PE fluctuations. The model also demonstrates efficacy in using transfer learning for PE computation, yielding a 7% margin improvement and a remarkable 35.3% reduction in RMSE for demand forecasts. Innovations in Cross-PE coefficient integration and price personalization have led to further margin enhancements. Moreover, the model excels in omnichannel pricing, achieving a 17.5% margin increase. Long-tailed product pricing using these PE values showed an increase in sales volume and revenue compared to traditional pricing strategies. Dyna-SPECTS prioritizes scalability using parallelization, distributed computing, and optimizing algorithms, efficiently managing a high volume of SKUs without compromising computational effectiveness and achieving rapid convergence. It represents a significant leap in dynamic price elasticity computation, offering a scalable, versatile, and empirically proven solution for e-commerce pricing challenges.
Kapitel in diesem Buch
- Frontmatter I
- Preface V
- Contents VII
-
Methods and instrumentation
- 1 Identifying and estimating outliers in time series with nonstationary mean through multiobjective optimization method 1
- 2 Using the intentionally linked entities (ILE) database system to create hypergraph databases with fast and reliable relationship linking, with example applications 21
- 3 Rapid and automated determination of cluster numbers for high-dimensional big data: a comprehensive update 37
- 4 Canonical correlation analysis and exploratory factor analysis of the four major centrality metrics 49
- 5 Navigating the landscape of automated data preprocessing: an in-depth review of automated machine learning platforms 71
- 6 Generating random XML 83
-
Applications and case studies
- 7 Exploring autism risk: a deep dive into graph neural networks and gene interaction data 105
- 8 Leveraging ChatGPT and table arrangement techniques in advanced newspaper content analysis for stock insights 121
- 9 An experimental study on road surface classification 145
- 10 RNN models for evaluating financial indices: examining volatility and demand-supply shifts in financial markets during COVID-19 165
- 11 Topological methods for vibration feature extraction 185
- 12 Dyna-SPECTS: DYNAmic enSemble of Price Elasticity Computation models using Thompson Sampling in e-commerce 215
- 13 Creating a metadata schema for reservoirs of data: a systems engineering approach 251
- 14 Implementation and evaluation of an eXplainable artificial intelligence to explain the evaluation of an assessment analytics algorithm for freetext exams in psychology courses in higher education to attest QBLM-based competencies 271
- 15 Toward a skill-centered qualification ontology supporting data mining of human resources in knowledge-based enterprise process representations 307
- Index 333
Kapitel in diesem Buch
- Frontmatter I
- Preface V
- Contents VII
-
Methods and instrumentation
- 1 Identifying and estimating outliers in time series with nonstationary mean through multiobjective optimization method 1
- 2 Using the intentionally linked entities (ILE) database system to create hypergraph databases with fast and reliable relationship linking, with example applications 21
- 3 Rapid and automated determination of cluster numbers for high-dimensional big data: a comprehensive update 37
- 4 Canonical correlation analysis and exploratory factor analysis of the four major centrality metrics 49
- 5 Navigating the landscape of automated data preprocessing: an in-depth review of automated machine learning platforms 71
- 6 Generating random XML 83
-
Applications and case studies
- 7 Exploring autism risk: a deep dive into graph neural networks and gene interaction data 105
- 8 Leveraging ChatGPT and table arrangement techniques in advanced newspaper content analysis for stock insights 121
- 9 An experimental study on road surface classification 145
- 10 RNN models for evaluating financial indices: examining volatility and demand-supply shifts in financial markets during COVID-19 165
- 11 Topological methods for vibration feature extraction 185
- 12 Dyna-SPECTS: DYNAmic enSemble of Price Elasticity Computation models using Thompson Sampling in e-commerce 215
- 13 Creating a metadata schema for reservoirs of data: a systems engineering approach 251
- 14 Implementation and evaluation of an eXplainable artificial intelligence to explain the evaluation of an assessment analytics algorithm for freetext exams in psychology courses in higher education to attest QBLM-based competencies 271
- 15 Toward a skill-centered qualification ontology supporting data mining of human resources in knowledge-based enterprise process representations 307
- Index 333
