Predicting Future Visitors Of Restaurants Using Big Data

Keogh

J. of Data, Inf. and Manag.

2022

The emergence of big data (BD) offers new opportunities for food businesses to address emerging risks and operational challenges. BD denotes the integration and analysis of multiple data sets, which are inherently complex, voluminous and are often of inadequate quality and structure. While BD is a well-established method in supply chain management, academic research on its application in the food ecosystem is still lagging. To fill this knowledge gap and capture the latest developments in this field, a systematic literature review was performed. Forty-one papers were selected and thoroughly examined and analysed to identify the enablers of BD in the food supply chain. The review primarily attempted to obtain an answer to the following research question: “What are the possibilities of leveraging big data in the food supply chain?“ Six significant benefits of applying BD in the food industry were identified, namely, the extraction of valuable knowledge and insights, decision-making support, improvement of food chain efficiencies, reliable forecasting, waste minimization, and food safety. Finally, some challenges and future research directions were outlined.

Section: Further Challenges Of Big Datamentioning

confidence: 99%

Big data in the food supply chain: a literature review

Keogh

J. of Data, Inf. and Manag.

2022

Proceedings of the International Conference of Applied Business and Management (ICABM2020)

“…For Ma, Tian, Luo and Zhang, the importance of big data when predicting future events based on data trends is quite significant. In this study they demonstrate how this technology can allow future visitors to a restaurant to be known, which allows expanding the competitiveness panorama and generating strategies to attract even more customers with the knowledge they are acquiring from them (Ma, 2018). The analysis of feelings and emotions is not far from this aspect of data processing, where feedback can show what feelings have been generated in consumers at the end of the experience, and be able to build improvements to the process of immersion (Micu, 2017).…”

Section: 5mentioning

confidence: 94%

Proceedings of the International Conference of Applied Business and Management (ICABM2020)

Borges¹

2020

Firms investment is a relevant element in economic growth. Therefore, it is important to consider the factors that influence it. In this context, the tax variable has a high impact on the investment decision. The purpose of this paper is to discuss how investing in intangible assets makes the computation of the effective corporate income tax rate especially complex. Methodology:The methodology applied is based on the method designated "legal research", in the legal-fiscal and accounting aspects. In this method, the analytical discussion of tax and accounting rules relevant to a given phenomenon allow us to assess the potential impact of a certain legal framework on business decisions.Originality: Economic models have traditionally incorporated the tax variable corresponding to the nominal rate of income tax for corporations. However, in the Portuguese tax legal framework there is a wide range of situations in which the tax framework differs from the accounting rules. When this happens, the nominal tax rate does not adequately capture the impact of the tax policy on investment results. This consideration is particularly relevant if the analysis focuses on investments that strongly integrate intangible elements into their composition Findings: Economic methodologies relating to investment and taxation will gain by specifying further the relationship between the nominal tax rate and the effective tax rate, particularly in the area of investments largely composed of intangible assets. Hypotheses of empirical investigation may follow from this study.Practical implications: At the corporate or macroeconomic level, the tax variable is increasingly complex in its determination. In fact, under corporate income tax, and for intangible assets, deductions to income, collection and other benefits can significantly create distance between nominal tax rate and effective tax rate. Research limitations:It is an analytical approach, which does not develop empirical studies, but leaves clues of statistical investigation.

“…Setelah melalui ekstraksi fitur, maka didapatkan 115 data pelanggan unik yang dapat digunakan dalam proses pelatihan dan pengujian. Hal ini dikarenakan, untuk memprediksi waktu kedatangan pelanggan di masa depan dibutuhkan data time series [22] dimana untuk membentuk data time series minimal terdapat 4 data kunjungan pelanggan ke dealer agar pelanggan tersebut memiliki data historis [23] yang cukup untuk membentuk time series. Data time series diekstrak ke dalam fitur Ddiff1, Ddiff2 dan Ddiff3 yang menghitung waktu selisih antar kedatangan pelanggan dengan kedatangan berikutnya.…”

Section: B Ektraksi Fiturunclassified

Prediksi Waktu Kedatangan Pelanggan Servis Kendaraan Bermotor Berdasarkan Data Historis menggunakan Support Vector Machine

Nugroho

Pradana

Nurfarida

2021

JEPIN

Dealer kendaraan perlu menjaga hubungan baik dengan pelanggan sehingga inti bisnis dealer dapat berlanjut dan berkembang. Salah satu strategi yang digunakan adalah memprediksi kapan pelanggan akan berkunjung lagi untuk servis kendaraan (layanan perawatan atau perbaikan kendaraan) berdasarkan analisis data riwayat kunjungan pelanggan. Dengan hasil prediksi berupa hari kedatangan pelanggan dimasa depan maka dealer kendaraan dapat mengingatkan pelanggan tentang kapan waktunya servis kendaraan. Support vector machine (SVM) adalah sebuah model pembelajaran mesin (machine learning) yang menggunakan hyperplane dan support-vector untuk memisahkan kelas dalam suatu ruang dimensi secara optimal sehingga sesuai untuk digunakan dalam pemecahan masalah prediksi waktu kedatangan pelanggan. SVM diimplementasikan untuk memprediksi kapan pelanggan akan datang lagi dimasa depan untuk perbaikan atau perawatan kendaraan. Hasil menunjukkan bahwa, dengan pemilihan metode yang tepat, SVM dapat memprediksi waktu kedatangan pelanggan dengan tingkat akurasi mencapai 92.5% berdasarkan validasi K-Fold cross-validation pada data latih dan mencapai rata-rata 97.33% untuk pengukuran nilai presisi, akurasi dan recall pada data uji