To create pricing policies, maximize resource allocation, and compete in a worldwide market, companies must have accurate estimates of price elasticity. Market supply and demand, seasonal fluctuations, economic cycles, policy control all challenge price elasticity models. Conventional statistical methods are unable to adequately represent dynamics in time series. In order to address the shortcomings of past approaches, this work presents the STL-GBM model, a dynamic price elasticity modeling and forecasting technique grounded on time series analysis and machine learning (ML). The model inputs trend and Seasonal and Trend decomposition using Loess (STL) decomposition into Gradient Boosting Machine (GBM) to anticipate price elasticity. High price elasticity prediction ability of STL-GBM is demonstrated by experimental validation on two real datasets, therefore highlighting the basic factors influencing price elasticity and providing companies with more informed decisions and market insight.
RezazadehJBagheriRKarimiS, et al.Examining the impact of product innovation and pricing capability on the international performance of exporting companies with the mediating role of competitive advantage for analysis and decision making. J Oper Intell2023; 1: 30–43.
2.
MitalMDel GiudiceMPapaA. Comparing supply chain risks for multiple product categories with cognitive mapping and Analytic Hierarchy Process. Technol Forecast Soc Change2018; 131: 159–170.
3.
AkpanIJUdohEAPAdebisiB. Small business awareness and adoption of state-of-the-art technologies in emerging and developing markets, and lessons from the COVID-19 pandemic. J Small Bus Enterpren2022; 34: 123–140.
4.
Al-OgailiASHashimTJTRahmatNA, et al.Review on scheduling, clustering, and forecasting strategies for controlling electric vehicle charging: challenges and recommendations. IEEE Access2019; 7: 128353–128371.
5.
NambiarMSimchi-LeviDWangH. Dynamic learning and pricing with model misspecification. Manag Sci2019; 65: 4980–5000.
6.
AntipovEAPokryshevskayaEB. Interpretable machine learning for demand modeling with high-dimensional data using Gradient Boosting Machines and Shapley values. J Revenue Pricing Manag2020; 19: 355–364.
DokumentovAHyndmanRJ. STR: seasonal-trend decomposition using regression. INFORMS J Data Sci2022; 1: 50–62.
9.
YaohaoPAlbuquerquePHM. Non-linear interactions and exchange rate prediction: empirical evidence using support vector regression. Appl Math Finance2019; 26: 69–100.
10.
SweetMMRArifMUddinA, et al.Credit risk assessment using statistical and machine learning: basic methodology and risk modeling applications. Int J Comput Eng2024; 1: 62–67.
11.
RuanGKirschenDSZhongH, et al.Estimating demand flexibility using Siamese LSTM neural networks. IEEE Trans Power Syst2021; 37: 2360–2370.
12.
DudekG. STD: a seasonal-trend-dispersion decomposition of time series. IEEE Trans Knowl Data Eng2023; 35: 10339–10350.
13.
AnghinoniLZhaoLJiD, et al.Time series trend detection and forecasting using complex network topology analysis. Neural Netw2019; 117: 295–306.
14.
WanjukiTMWagalaAMuriithiDK. Evaluating the predictive ability of seasonal autoregressive integrated moving average (SARIMA) models using food and beverages price index in Kenya. Eur J Math Statis2022; 3: 28–38.
15.
SallesRBellozeKPortoF, et al.Nonstationary time series transformation methods: an experimental review. Knowl Base Syst2019; 164: 274–291.
16.
UsamiS. On the differences between general cross-lagged panel model and random-intercept cross-lagged panel model: interpretation of cross-lagged parameters and model choice. Struct Equ Model: A Multidiscip J2021; 28: 331–344.
17.
OjoJFOlanrewajuRO. Review of family of autoregressive integrated moving average models in the comportment of autocorrelation function for non-seasonal time series data. Int J Math Sci Appl2021; 19: 79–89.
18.
AbonazelMRAbd-ElftahAI. Forecasting Egyptian GDP using ARIMA models. Reports on Economics and Finance2019; 5: 35–47.
SanzHValimCVegasE, et al.SVM-RFE: selection and visualization of the most relevant features through non-linear kernels. BMC Bioinf2018; 19: 1–18.
21.
YangJMaJ. Feed-forward neural network training using sparse representation. Expert Syst Appl2019; 116: 255–264.
22.
FriedrichSGrollAIckstadtK, et al.Regularization approaches in clinical biostatistics: a review of methods and their applications. Stat Methods Med Res2023; 32: 425–440.
23.
GarbinCZhuXMarquesO. Dropout vs. batch normalization: an empirical study of their impact to deep learning. Multimed Tool Appl2020; 79: 12777–12815.
24.
ChenDZhangJJiangS. Forecasting the short-term metro ridership with seasonal and trend decomposition using loess and LSTM neural networks. IEEE Access2020; 8: 91181–91187.
25.
MihaiSYaqoobMHungDV, et al.Digital twins: a survey on enabling technologies, challenges, trends and future prospects. IEEE Commun Surv Tutorials2022; 24: 2255–2291.
26.
BhartiJPMishraPmoorthyU, et al.Slope stability analysis using Rf, gbm, cart, bt and xgboost. Geotech Geol Eng2021; 39: 3741–3752.
27.
LinSZhengHHanB, et al.Comparative performance of eight ensemble learning approaches for the development of models of slope stability prediction. Acta Geotech2022; 17: 1477–1502.
28.
BaqueroRABarbosaAMAyllónD, et al.Potential distributions of invasive vertebrates in the Iberian Peninsula under projected changes in climate extreme events. Divers Distrib2021; 27: 2262–2276.
29.
ParkYHoJC. Tackling overfitting in boosting for noisy healthcare data. IEEE Trans Knowl Data Eng2019; 33: 2995–3006.
30.
BauerJJannachD. Optimal pricing in e-commerce based on sparse and noisy data. Decis Support Syst2018; 106: 53–63.
31.
WenLYeXGaoL. A new automatic machine learning based hyperparameter optimization for workpiece quality prediction. Measurement and Control2020; 53: 1088–1098.
32.
FanF-LXiongJLiM, et al.On interpretability of artificial neural networks: a survey. IEEE Trans Radiat Plasma Med Sci2021; 5: 741–760.
33.
VelosoBGamaJMalheiroB, et al.Hyperparameter self-tuning for data streams. Inf Fusion2021; 76: 75–86.
