A data-driven forecasting approach for newly launched seasonal products by leveraging machine-learning approaches

Abstract

Companies in the fashion industry are struggling with forecasting demand due to the short-selling season, long lead times between the operations, huge product variety and ambiguity of demand information. The forecasting process is becoming more complicated by virtue of evolving retail technology trends. Demand volatility and speed are highly affected by e-commerce strategies as well as social media usage regards to varying customer preferences, short product lifecycles, obsolescence of the retail calendar, and lack of information for newly launched seasonal items. Consumers have become more demanding and less predictable in their purchasing behavior that expects high quality, guaranteed availability and fast delivery. Meeting high expectations of customers' initiates with proper demand management.This study focuses on demand prediction with a data-driven perspective by both leveraging machine learning techniques and identifying significant predictor variables to help fashion retailers achieve better forecast accuracy. Prediction results obtained were compared to present the benefits of machine learning approaches. The proposed approach was applied by a leading fashion retail company to forecast the demand of newly launched seasonal products without historical data.

The derived demand for advertising expenses and implications on sustainability: a comparative study using deep learning and traditional machine learning methods

“…Traditional demand forecasting methods predict future values based on time series that analyze limited historical demand data. Some of them include Delphi method, grass roots forecasting, trend analysis, multi-regression model, moving averages, Croston's method, time series model, exponential correction and ARIMA (Alon et al, 2001;Bollapragada et al, 2008;Chen et al, 2000;Kharfan et al, 2020). These methods have been found to be effective only when factors such as nature trends and seasonal factors are not considered.…”

“…Given the predictive ability of ML, one of the most prominent problems of marketing is to improve demand forecasting as this is vital for customer satisfaction, product planning and supply chain management (Boone et al, 2019;Carbonneau et al, 2008;Kharfan et al, 2020;Zhu et al, 2021) and predict the stock market movement (Eachempati et al, 2021). ML uses several forecasting methods such as Neural Network, Fuzzy Neural Network, Artificial Neural Network, Recurrent Neural Networks, Genetic Algorithm, Support Vector Regression, Random Forest Regressor, Decision Tree Regressor etc.…”

Post-script—Retail forecasting: Research and practice

“…For example, Huber and Stuckenschmidt (2020) provided evidence that global ML models (feed-forward and recurrent neural networks, gradient boosted regression trees) could achieve a higher forecast accuracy compared to time series models with adjustments or a regularised linear regression model, and the ranking of the evaluated methods remained constant over different horizons. Kharfan, Chan, and Efendigil (2020) applied an ML pipeline comprising clustering, classification and prediction to forecast newly launched fashion products. Punia, Singh, and Madaan (2020) calculated coherent hierarchical forecasts in a multidimensional hierarchy comprising location, product and online vs. offline channels, again using an LSTM.…”

The Use of Intervention Approach in Individual and Aggregate Forecasting Methods for Burger Patties: A Case in Indonesia

“…The qualitative approach involves individual perception to figure out the unusual data points and adjust them before the data were processed quantitatively (Pradita et al, 2020). Kharfan, Chan, and Efendigil (2021) studied a data-driven methodology to improve the demand forecasting procedure for fashion retailers for recently launched products without historical data in a vigorous market situation. The results showed that the three-step model delivers visibility of core factors that influence demand through clustering and classification.…”