This paper proposes a new approach to sales forecasting for new products with long lead time but short product life cycle. These SKUs are usually sold for one season only, without any replenishments. An exponential factorization machine (EFM) sales forecast model is developed to solve this problem which not only considers SKU attributes, but also pairwise interactions. The EFM model is significantly different from the original Factorization Machines (FM) from two-fold: (1) the attribute-level formulation for explanatory variables and (2) exponential formulation for the positive response variable. The attribute-level formation excludes infeasible intra-attribute interactions and results in more efficient feature engineering comparing with the conventional one-hot encoding, while the exponential formulation is demonstrated more effective than the log-transformation for the positive but not skewed distributed responses. In order to estimate the parameters, percentage error squares (PES) and error squares (ES) are minimized by a proposed adaptive batch gradient descent method over the training set. Real-world data provided by a footwear retailer in Singapore is used for testing the proposed approach. The forecasting performance in terms of both mean absolute percentage error (MAPE) and mean absolute error (MAE) compares favourably with not only off-the-shelf models but also results reported by extant sales and demand forecasting studies. The effectiveness of the proposed approach is also demonstrated by two external public datasets. Moreover, we prove the theoretical relationships between PES and ES minimization, and present an important property of the PES minimization for regression models; that it trains models to underestimate data. This property fits the situation of sales forecasting where unit-holding cost is much greater than the unit-shortage cost.
翻译:本文提出了一种新的方法来预测周期较长但产品寿命周期较短的新产品的销售情况。 这些 SKU 通常只销售一个季节,不作任何补充。 一个指数化指数化指数化计算机(EFM) 销售预测模型(EFM) 是为了解决这个问题,不仅考虑到SKU属性,而且还考虑到双向互动。 EFM 模型与最初的保理化机器(FM) 明显不同,有两重:(1) 解释变量的属性级配方和(2) 积极响应变量的指数级配方。 属性级的形成排除了不可行的内部归属性互动,并导致与常规的单热值计算相比,更高效的特性工程设计,而指数化的配方则比正态化的对正态化计算法更有效。 为了估算参数,将百分率方位差(PES)和误差方(ES)与培训集的拟议调制分批递增梯度递增基底值计算方法相比,新加坡鞋零售商提供的实时数据用于测试拟议方法。 以绝对性比例差的绝对性比率模型预测绩效模型(MA ) 和绝对性估算成本值数据(E),以我们所报算的估算值估算值比的外部数据(E) 和绝对值的估算值的估算值的汇率值比) 和绝对值数据(我们所报价值的估算值的汇率值的汇率的估算值值),以两种方法,用成本值比,只有两种方法。