A machine learning-based framework for forecasting sales of new products with short life cycles using deep neural networks

Elalem, Yara Kayyali; Maier, Sebastian; Seifert, Ralf W.

doi:10.1016/j.ijforecast.2022.09.005

Cited by 16 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other important models of the support vector machine (SVM), the deep neural network (DNN), and the convolutional neural network (CNN) are also considered as benchmarking models. While the CNN was originally applied to image analysis, in many recent studies, the CNN has been applied to forecasting of time series such as stock price, volatility, and many others, see Vidal and Kristjanpoller (2020), Elalem et al (2023), Liang et al (2022), Choi and Shin (2022). This is because CNN captures local features of a time series and has a lower computational cost than the RNN.…”

Section: Forecast Resultsmentioning

confidence: 99%

Forecasting realized volatility using data normalization and recurrent neural network

Lee,

Shin,

Choi

2024

Communications for Statistical Applications and Methods

View full text Add to dashboard Cite

We propose recurrent neural network (RNN) methods for forecasting realized volatility (RV). The data are RVs of ten major stock price indices, four from the US, and six from the EU. Forecasts are made for relative ratio of adjacent RVs instead of the RV itself in order to avoid the out-of-scale issue. Forecasts of RV ratios distribution are first constructed from which those of RVs are computed which are shown to be better than forecasts constructed directly from RV. The apparent asymmetry of RV ratio is addressed by the Piecewise Minmax (PM) normalization. The serial dependence of the ratio data renders us to consider two architectures, long short-term memory (LSTM) and gated recurrent unit (GRU). The hyperparameters of LSTM and GRU are tuned by the nested cross validation. The RNN forecast with the PM normalization and ratio transformation is shown to outperform other forecasts by other RNN models and by benchmarking models of the AR model, the support vector machine (SVM), the deep neural network (DNN), and the convolutional neural network (CNN).

show abstract

Section: Forecast Resultsmentioning

confidence: 99%

Forecasting realized volatility using data normalization and recurrent neural network

Lee,

Shin,

Choi

2024

Communications for Statistical Applications and Methods

View full text Add to dashboard Cite

show abstract

“…With the development of Internet technology and the wide application of big data, online and offline shopping methods have brought consumers a more convenient consumption experience [5]. But at the same time, for brick-and-mortar supermarkets, the competition is more intense [6].…”

Section: Introductionmentioning

confidence: 99%

Commodity Sales Forecast Based on Cluster Analysis and Time Series

Lu,

Ren

2024

Proceedings of the 4th International Conference on Economic Management and Big Data Applications, ICEMBDA 2023, October 27–29,

View full text Add to dashboard Cite

The price of vegetables in fresh supermarkets is affected by many factors such as time and sales. Reliable market demand analysis is especially important for replenishment and pricing decisions. This article delves into related issues in vegetable pricing. We select the sales data of the latest 2023 Mathematical Modeling Competition Question C as the data in this paper, first preprocess the data, summarize the data according to vegetable categories and single products every day, and observe the sales trend of categories and single products over time by drawing a line chart. Second, the distribution of the data is tested, and the P-P plot of each variable is drawn to determine whether it follows a normal distribution; Pearson correlation analysis and Spearman correlation analysis were used to calculate the correlation coefficient between categories and items, respectively. According to the correlation coefficient test, the model is not significant. Therefore, cluster analysis is used to explore the correlation between each vegetable category and a single product, and the cluster analysis lineage map is drawn to visually represent the correlation between each category and a single product. The data is then aggregated to plot a scatter plot between sales and cost plus price to observe possible functional relationships between them. Linear regression, loglinear regression and polynomial regression were used to train the data, plot the function curve and data scatter plot, and calculate the evaluation indicators of the regression model. The time series model is used to predict the sales volume of each category in the next week, and the relationship between sales volume and cost plus price is trained into the time series model as a penalty function. Finally, get the best replenishment volumes and pricing for each category next week so that merchants can get the highest profits.

show abstract

“…Thus, recent studies encompass a broad spectrum of models, ranging from simple linear approaches like autoregressive integrated moving average (ARIMA) [1][2][3][4][5][6], seasonal ARIMA (SARIMA) [7][8][9][10], and ARIMA exogenous variable models (ARIMAX) [11][12][13],…”

Section: Introductionmentioning

confidence: 99%

Elevating Univariate Time Series Forecasting: Innovative SVR-Empowered Nonlinear Autoregressive Neural Networks

Borrero,

Mariscal

2023

Algorithms

View full text Add to dashboard Cite

Efforts across diverse domains like economics, energy, and agronomy have focused on developing predictive models for time series data. A spectrum of techniques, spanning from elementary linear models to intricate neural networks and machine learning algorithms, has been explored to achieve accurate forecasts. The hybrid ARIMA-SVR model has garnered attention due to its fusion of a foundational linear model with error correction capabilities. However, its use is limited to stationary time series data, posing a significant challenge. To overcome these limitations and drive progress, we propose the innovative NAR–SVR hybrid method. Unlike its predecessor, this approach breaks free from stationarity and linearity constraints, leading to improved model performance solely through historical data exploitation. This advancement significantly reduces the time and computational resources needed for precise predictions, a critical factor in univariate economic time series forecasting. We apply the NAR–SVR hybrid model in three scenarios: Spanish berry daily yield data from 2018 to 2021, daily COVID-19 cases in three countries during 2020, and the daily Bitcoin price time series from 2015 to 2020. Through extensive comparative analyses with other time series prediction models, our results substantiate that our novel approach consistently outperforms its counterparts. By transcending stationarity and linearity limitations, our hybrid methodology establishes a new paradigm for univariate time series forecasting, revolutionizing the field and enhancing predictive capabilities across various domains as highlighted in this study.

show abstract

A machine learning-based framework for forecasting sales of new products with short life cycles using deep neural networks

Cited by 16 publications

References 38 publications

Forecasting realized volatility using data normalization and recurrent neural network

Forecasting realized volatility using data normalization and recurrent neural network

Commodity Sales Forecast Based on Cluster Analysis and Time Series

Elevating Univariate Time Series Forecasting: Innovative SVR-Empowered Nonlinear Autoregressive Neural Networks

Contact Info

Product

Resources

About