How effective are neural networks at forecasting and prediction? A review and evaluation

By Monica P. Adya, F. Collopy. 1998

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Leverage Financial News to Predict Stock Price Movements Using Word Embeddings and Deep Neural Networks (2015, methodology): “Traditionally neural networks have been used to model stock prices as time series for the forecasting purpose, such as in (Kaastra and Boyd, 1991; Adya and Collopy, 1991; Chan et al., 2000; Skabar and Cloete, 2002; Zhu et al., 2008).”
Intermittent demand forecasts with neural networks (2013, background): “Adya and Collopy (1998) found that of 73% of the papers reviewed NNs to outperform established benchmarks.”
Toward Automatic Time-Series Forecasting Using Neural Networks (2012, background): “overview papers, for example, [1], [8], [17], provide a good”
Avoiding Pitfalls in Neural Network Research (2007, background): “The lack of transparency, thus, contributes to errors in published research work.”
Layered Ensemble Architecture for Time Series Forecasting (2016, methodology): “The proposed LEA applies a simple deseasonalization procedure suggested in [42] on the seasonal time series of NN3.”
25 years of time series forecasting (2006, result): “These observations are consistent with the results of an evaluating research by Adya and Collopy (1998), on the effectiveness of ANNbased forecasting in 48 studies done between 1988 and 1994.”
Forecasting across time series databases using recurrent neural networks on groups of similar series: A clustering approach (2017, background): “Also, careful selection of network parameters with the right choice of model architectures have proven that now NNs can be a strong alternative to traditional statistical forecasting methods (Adya and Collopy, 1998; Zhang et al., 1998; Crone et al., 2011).”
Machine Learning in Financial Crisis Prediction: A Survey (2012, background): “of bankruptcy-prediction and credit-scoring models since the 1990s [1], [35], [44], [169].”
Neural Networks In Business Time Series Forecasting: Benefits And Problems (2011, methodology): “The results from these comparisons are mixed and confounding (Adya & Collopy, 1998).”
A comparative study of linear and nonlinear models for aggregate retail sales forecasting (2003, unknown): “Although numerous comparative studies be-tween traditional models and neural networks have been conducted in the literature, ﬁndings are mixed with regard to whether the ﬂexible non-linear approach is better than the linear method in forecasting (Adya and Collopy, 1998).”
Forecast combinations of computational intelligence and linear models for the NN5 time series forecasting competition (2011, methodology): “…forecasting problem, and their performance is quite encouraging (see for example Alon, Qi, & Sadowski, 2001; Callen, Kwan, Yip, & Yuan, 1996; Hill, O'Connor, & Remus, 1996; Sharda & Patil, 1992; Terasvirta, van Dijk, & Medeiros, 2005; Zhang & Qi, 2005; and the review by Adya & Collopy, 1998).”