drawing different graphs to interpret their results
preliminary, the owner and people working there
hardly accepted their conclusions and insisted their
focus on the website and the digital ordering process.
They even showed scepticism when prediction values
failed to meet their perceived expectations though
researchers stressed that their ideas were only
references (Fries & Ludwig, 2024).
Consequently, transparency and interpretability are
essential for unfolding the full potential of various
ML-based models because they ensure clear answers
to two basic questions regarding how the model
works and what the model implies (Fries and Ludwig,
2024). To resolve the trust issue, formulating more
targeted and convincing sales prediction schemes
based on these attractive approaches for diverse
industries would help.
6 CONCLUSIONS
To sum up, sales prediction is helpful in sales
planning to achieve sales at or near the level of
customer demand. It pertains to the proper use of
various techniques, both qualitative and quantitative,
within the context of corporate information systems.
The most efficient forecasting methods these days are
stochastic models and ML algorithms, such as
ARIMA, and LSTM, and their hybrid models that can
easily fetch linear and non-linear sales trends. In most
cases, a hybrid model tends to outperform its single
models by obtaining lower MSE or RMSE. For
example, an integrated LSTM-ARIMA model shows
higher accuracy than a single ARIMA model and an
LSTM-based network. Nevertheless, those intricate
ML-based models are often hard to explain in actual
applications, thus rarely fulfilling their role in making
practical plans. Therefore, despite the continual
innovation in more sophisticated methods, more
attempts to fill this gap are being urged to attain more
functional and informative forecasts. The present
article aims to motivate more follow-up practitioners
to enable sales prediction to keep evolving with the
times and satisfy the needs of more businesses.
REFERENCES
Byrne, T. M. M., Moon, M. A., Mentzer, J. T., 2011.
Motivating the industrial sales force in the sales
forecasting process. Industrial Marketing Management,
40(1), 128-138.
Cao, H., Zhu, C., 2004. Management Accounting. Tsinghua
University publishing house co., ltd.
Chen, Z., 1987. Management Accounting - Chapter IV
Sales Prediction. Shanghai Accounting, 9.
Dave, E., Leonardo, A., Jeanice, M., Hanafiah, N., 2021.
Forecasting Indonesia exports using a hybrid model
ARIMA-LSTM. Procedia Computer Science, 179, 480-
487.
Dalrymple, D. J., 1975. Sales forecasting methods and
accuracy. Business Horizons, 18(6), 69-73.
Ferber, R., 1955. Sales Forecasting by Sample Surveys.
Journal of Marketing, 20(1), 1-13.
Fries, M., Ludwig, T., 2024. Why are the sales forecasts so
low socio-technical challenges of using machine
learning for forecasting sales in a bakery. Computer
Supported Cooperative Work (CSCW), 33(2), 253-293.
Huang, W., Zhang, Q., Xu, W., Fu, H., Wang, M., Liang, X.,
2015. A novel trigger model for sales prediction with
data mining techniques. Data Science Journal, 14, 15-15.
Lawrence, M., Goodwin, P., O'Connor, M., Önkal, D., 2006.
Judgmental forecasting: A review of progress over the
last 25 years. International Journal of forecasting, 22(3),
493-518.
Linstone, H. A., 1985. The delphi technique. In
Environmental impact assessment, technology
assessment, and risk analysis: contributions from the
psychological and decision sciences. Berlin, Heidelberg:
Springer Berlin Heidelberg.
Qiu X., 2020. Neural Networks and Deep Learning. China
Machine Press.
Sherstinsky, A., 2020. Fundamentals of Recurrent Neural
Network (RNN) and Long Short-Term Memory (LSTM)
network. Physica D: Nonlinear Phenomena, 404,
132306.
Shumway, R. H., Stoffer, D. S., Shumway, R. H., Stoffer,
D. S., 2017. ARIMA models. Time series analysis and
its applications: with R examples, Springer, 75-163.
Sirisha, U. M., Belavagi, M. C., Attigeri, G., 2022. Profit
prediction using ARIMA, SARIMA and LSTM models in
time series forecasting: A comparison. IEEE Access, 10,
124715-124727.
Swami, D., Shah, A. D., Ray, S. K., 2020. Predicting future
sales of retail products using machine learning. arXiv
preprint arXiv:2008.07779.
Vavliakis, K. N., Siailis, A., Symeonidis, A. L., 2021.
Optimizing Sales Forecasting in e-Commerce with
ARIMA and LSTM Models. In WEBIST (pp. 299-306).
Wallsten, T. S., Budescu, D. V., Erev, I., Diederich, A.,
1997. Evaluating and combining subjective probability
estimates. Journal of Behavioral Decision Making,
10(3), 243-268.
Wang Y., 2020. Time Series Analysis with R. China Renmin
University Press.
Yang M., Rong Y., Wang S., 1985. Chapter V Sales
Forecasting Methods. Modern Finance And Economics
- Journal of Tianjin University of Finance And
Economics, 4.
Yu, Y., Si, X., Hu, C., Zhang, J., 2019. A review of
recurrent neural networks: LSTM cells and network
architectures. Neural computation, 31(7), 1235-1270.