{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T19:45:47Z","timestamp":1765827947429,"version":"build-2065373602"},"reference-count":36,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2020,8,15]],"date-time":"2020-08-15T00:00:00Z","timestamp":1597449600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>A Long Short Term Memory (LSTM) based sales model has been developed to forecast the global sales of hotel business of Travel Boutique Online Holidays (TBO Holidays). The LSTM model is a multivariate model; input to the model includes several independent variables in addition to a dependent variable, viz., sales from the previous step. One of the input variables, \u201cnumber of active bookers per day\u201d, is estimated for the same day as sales. This need for estimation requires the development of another LSTM model to predict the number of active bookers per day. The number of active bookers is variable, so the predicted is used as an input to the sales forecasting model. The use of a predicted variable as an input variable to another model increases the chance of uncertainty entering the system. This paper discusses the quantum of variability observed in sales predictions for various uncertainties or noise due to the estimation of the number of active bookers. For the purposes of this study, different noise distributions such as normalized, uniform, and logistic distributions are used, among others. Analyses of predictions demonstrate that the addition of uncertainty to the number of active bookers via dropouts as well as to the lagged sales variables leads to model predictions that are close to the observations. The least squared error between observations and predictions is higher for uncertainties modeled using other distributions (without dropouts) with the worst predictions being for Gumbel noise distribution. Gaussian noise added directly to the weights matrix yields the best results (minimum prediction errors). One possibility of this uncertainty could be that the global minimum of the least squared objective function with respect to the model weight matrix is not reached, and therefore, model parameters are not optimal. The two LSTM models used in series are also used to study the impact of corona virus on global sales. By introducing a new variable called the corona virus impact variable, the LSTM models can predict corona-affected sales within five percent (5%) of the actuals. The research discussed in the paper finds LSTM models to be effective tools that can be used in the travel industry as they are able to successfully model the trends in sales. These tools can be reliably used to simulate various hypothetical scenarios also.<\/jats:p>","DOI":"10.3390\/make2030014","type":"journal-article","created":{"date-parts":[[2020,8,17]],"date-time":"2020-08-17T04:35:51Z","timestamp":1597638951000},"page":"256-270","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Impact of Uncertainty in the Input Variables and Model Parameters on Predictions of a Long Short Term Memory (LSTM) Based Sales Forecasting Model"],"prefix":"10.3390","volume":"2","author":[{"given":"Shakti","family":"Goel","sequence":"first","affiliation":[{"name":"Chief Data and Analytics Officer, TBO Holidays, TEK Travels, Gurugram, Haryana 122022, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rahul","family":"Bajpai","sequence":"additional","affiliation":[{"name":"Senior Machine Learning Engineer, TBO Holidays, TEK Travels, Gurugram, Haryana 122022, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,8,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.neucom.2017.03.040","article-title":"Expectile regression neural network model with applications","volume":"247","author":"Jiang","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.compag.2017.03.024","article-title":"Smart frost control in greenhouses by neural networks models","volume":"137","year":"2017","journal-title":"Comput. Electron. Agric."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.ejor.2017.08.056","article-title":"Rule-based autoregressive moving average models for forecasting load on special days: A case study for France","volume":"266","author":"Arora","year":"2018","journal-title":"Eur. J. Oper. Res."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.inffus.2017.08.004","article-title":"Multistage fusion approaches based on a generative model and multivariate exponentially weighted moving average for diagnosis of cardiovascular autonomic nerve dysfunction","volume":"41","author":"Hassan","year":"2018","journal-title":"Inf. Fusion"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"113637","DOI":"10.1016\/j.eswa.2020.113637","article-title":"Automatic robust estimation for exponential smoothing: Perspectives from statistics and machine learning","volume":"160","author":"Barrow","year":"2020","journal-title":"Expert Syst. Appl."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1016\/j.neucom.2019.07.088","article-title":"A hybrid artificial neural network-GJR modeling approach to forecasting currency exchange rate volatility","volume":"365","author":"Bafffour","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"108043","DOI":"10.1016\/j.measurement.2020.108043","article-title":"Smart frost measurement for anti-disaster intelligent control in greenhouses via embedding IoT and hybrid AI methods","volume":"164","year":"2020","journal-title":"Measurement"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1016\/j.cor.2018.05.020","article-title":"Soft computing hybrids for FOREX rate prediction: A comprehensive review","volume":"99","author":"Pradeepkumar","year":"2018","journal-title":"Comput. Oper. Res."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.engappai.2017.07.007","article-title":"A hybrid ETS\u2013ANN model for time series forecasting","volume":"66","author":"Panigrahi","year":"2017","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.neucom.2019.05.099","article-title":"Improving forecasting accuracy of time series data using a new ARIMA-ANN hybrid method and empirical mode decomposition","volume":"361","author":"Buyuksahin","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_11","unstructured":"Siami, N.S., Tavakoli, N., and Siami, N.A. (2018, January 17\u201320). A Comparison of ARIMA and LSTM in Forecasting Time Series. Proceedings of the 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), Orlando, FL, USA."},{"key":"ref_12","first-page":"e27712v1","article-title":"Sales forecasting using multivariate long shortterm memory network models","volume":"7","author":"Helmini","year":"2019","journal-title":"PeerJ PrePrints"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Graves, A. (2013). Generating sequences with recurrent neural networks. arXiv.","DOI":"10.1007\/978-3-642-24797-2_3"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhu, L., and Laptev, N. (2017, January 18\u201321). Deep and Confident Prediction for Time Series at Uber. Proceedings of the 2017 IEEE International Conference on Data Mining Workshops (ICDMW); Institute of Electrical and Electronics Engineers (IEEE), New Orleans, LA, USA.","DOI":"10.1109\/ICDMW.2017.19"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Alonso, A.M., Nogales, F.J., and Ruiz, C. (2019). A Single Scalable LSTM Model for Short-Term Forecasting of Disaggregated Electricity Loads. arXiv.","DOI":"10.3390\/en13205328"},{"key":"ref_16","unstructured":"Gal, Y., and Ghahramani, Z. (2015). Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"De Franco, C., Nicolle, J., and Pham, H. (2019). Dealing with Drift Uncertainty: A Bayesian Learning Approach. Risks, 7.","DOI":"10.3390\/risks7010005"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"36218","DOI":"10.1109\/ACCESS.2018.2836917","article-title":"Neural Network-Based Uncertainty Quantification: A Survey of Methodologies and Applications","volume":"6","author":"Kabir","year":"2018","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"991","DOI":"10.1007\/s13042-017-0777-2","article-title":"Per-sample prediction intervals for extreme learning machines","volume":"10","author":"Akusok","year":"2018","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1038\/nature14541","article-title":"Probabilistic machine learning and artificial intelligence","volume":"521","author":"Ghahramani","year":"2015","journal-title":"Nature"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"809","DOI":"10.1038\/nmeth.2613","article-title":"Points of significance: Importance of being uncertain","volume":"10","author":"Krzywinski","year":"2013","journal-title":"Nat. Methods"},{"key":"ref_22","first-page":"859","article-title":"Estimation under model uncertainty","volume":"27","author":"Longford","year":"2017","journal-title":"Stat. Sin."},{"key":"ref_23","unstructured":"Chen, G. (2016). A Gentle Tutorial of Recurrent Neural Network with Error Backpropagation. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Ben Taieb, S., Bontempi, G., Atiya, A.F., and Sorjamaa, A. (2011). A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition. arXiv.","DOI":"10.1016\/j.eswa.2012.01.039"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1152","DOI":"10.4236\/am.2014.58108","article-title":"The Application of Time Series Modelling and Monte Carlo Simulation: Forecasting Volatile Inventory Requirements","volume":"5","author":"Davies","year":"2014","journal-title":"Appl. Math."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1261","DOI":"10.1109\/72.809073","article-title":"Bayesian approach to neural-network modeling with input uncertainty","volume":"10","author":"Wright","year":"1999","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_27","unstructured":"Labach, A., Salehinejad, H., and Valaee, S. (2019). Survey of Dropout Methods for Deep Neural Networks. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1177\/0008068320030104","article-title":"Estimation of the Parameters of Triangular Distribution by Order Statistics","volume":"54","author":"Samuel","year":"2003","journal-title":"Calcutta Stat. Assoc. Bull."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1177\/0008068320040310","article-title":"On Logistic and Generalized Logistic Distributions","volume":"55","author":"Gupta","year":"2004","journal-title":"Calcutta Stat. Assoc. Bull."},{"key":"ref_30","first-page":"523","article-title":"Discriminating Between Normal and Gumbel Distributions","volume":"15","author":"Qaffou","year":"2017","journal-title":"REVSTAT Stat. J."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"432642","DOI":"10.1155\/2013\/432642","article-title":"On the Generalized Lognormal Distribution","volume":"2013","author":"Toulias","year":"2013","journal-title":"J. Probab. Stat."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"734575","DOI":"10.1155\/2012\/734575","article-title":"Interval Estimations of the Two-Parameter Exponential Distribution","volume":"2012","author":"Jiang","year":"2012","journal-title":"J. Probab. Stat."},{"key":"ref_33","unstructured":"Ognawala, S., and Bayer, J. (2014). Regularizing recurrent networks\u2014On injected noise and norm-based methods. arXiv."},{"key":"ref_34","unstructured":"Li, Y., and Liu, F. (2018). Whiteout: gaussian adaptive noise injection regularization in deep neural networks. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1424","DOI":"10.1109\/72.548170","article-title":"An analysis of noise in recurrent neural networks: Convergence and generalization","volume":"7","author":"Jim","year":"1996","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Student (1908). The Probable Error of a Mean. Biometrika, 6, 1\u201325.","DOI":"10.1093\/biomet\/6.1.1"}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/2\/3\/14\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:01:33Z","timestamp":1760176893000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/2\/3\/14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,15]]},"references-count":36,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2020,9]]}},"alternative-id":["make2030014"],"URL":"https:\/\/doi.org\/10.3390\/make2030014","relation":{},"ISSN":["2504-4990"],"issn-type":[{"type":"electronic","value":"2504-4990"}],"subject":[],"published":{"date-parts":[[2020,8,15]]}}}