APPLICATION OF STATISTICAL METHODS, CLUSTER ANALYSIS AND NEURAL NETWORK TECHNOLOGIES IN FORECASTING PROCUREMENT PRICES FOR MEDICINES

About

News

Aims and Scope

Founder and Publisher

Editorial board

Licensing terms

Privacy Statement

Plagiarism policy

Publication ethics

Archiving Policy

Subscription

For Authors

Instructions for authors

Reviewing proccess

Copyright Notice

License agreement

Article processing charges

Archive

All issues

Search

Contacts

Contacts

N. Andrievskaya
Federal State Budgetary Educational Institution of Higher Education "Donetsk National Technical University" , Donetsk
Research interests: ontological design, semantic technologies, intelligent management methods.

T. Martynenko
Federal State Budgetary Educational Institution of Higher Education "Donetsk National Technical University" , Donetsk
Research interests: video information analysis, machine learning, modern optimization methods, intelligent management methods.

T. Vasyaeva
Federal State Budgetary Educational Institution of Higher Education "Donetsk National Technical University" , Donetsk
Research interests: machine learning, neural network and evolutionary modeling, methods and systems of artificial intelligence.

Download pdf

UDC 004.048
DOI 10.34757/2413-7383.2023.31.4.005
Language: Russian
Annotation:The article discusses the problem of planning the procurement of medicines in a pharmacy chain. When determining the optimal purchase price, there is a need to forecast prices using a historical array of price list data. Traditional statistical approaches to forecasting, as well as methods based on a neural network, are analyzed. Four methods are implemented: moving average method; random forest method; K-nearest neighbors’ method; neural network with LSTM architecture. Based on a number of metrics, the quality of the forecast of the tested methods was assessed. The experiments performed showed high prediction accuracy.
Keywords: neural network, LSTM, procurement, forecasting, forecast method, forecast accuracy.

References:
1. Svetlichnaya V.A. Ispol'zovanie metodov teorii prinyatiya reshenij dlya vybora optimal'noj strategii pri zakupke lekarstvennyh sredstv / V.A. Svetlichnaya, E.A. SHumaeva, O.V. CHengar', A.V. Andrievskaya // Ekonomika stroitel'stva i gorodskogo hozyajstva. 2020. – T. 16. № 1. – S. 41-48.
2. Zolotova I.YU. Kratkosrochnoe prognozirovanie cen na rossijskom optovom rynke elektroenergii na osnove nejronnyh setej / I.YU. Zolotova, V.V. // Problemy prognozirovaniya. 2017.
3. Andrievskaya, A.V. Ekstrapolyacionnye metody prognozirovaniya zakupochnyh cen lekarstv v usloviyah aptechnoj seti / A.V. Andrievskaya, V.O. Vovchenko, N.K. Andrievskaya // Informatika, upravlyayushchie sistemy, matematicheskoe i komp'yuternoe modelirovanie (IUSMKM-2021). Materialy XII Mezhdunarodnojnauchno-tekhnicheskoj konferencii v ramkah VII Mezhdunarodnogo Nauchnogo foruma Doneckoj Narodnoj Respubliki k 100-letiyu DonNTU. 2021, 169-175
4. Metod skol'zyashchej srednej v statistike [Elektronnyj resurs] – URL: https://www.goodstudents.ru/statistikazadachi/1144-metod-skolzyashej-srednej.html// (data obrashcheniya: 19.05.2023).
5. Feature selection for time-series prediction in case of undetermined estimation. Khmilovyi S., Skobtsov Yu., Vasyaeva T., Andrievskaya N.V sbornike: Biologically Inspired Cognitive Architectures (BICA) for Young Scientists. Proceedings of the First International Early Research Career Enhancement School (FIERCES 2016). Cham, 2016. S. 85-97
6. Hairova S.M. Metodika raboty s postavshchikami na osnove modelirovaniya raboty nejronnoj seti pri reshenii voprosov vybora postavshchikov uslug // Hairova S.M., Hairov B.G., SHimohin A.V. / FUNDAMENTAL'NYE ISSLEDOVANIYA № 7, 2020
7. Hajrutdinov M.R. Primenenie nejronnoj seti s obratnym rasprostraneniem i nejronnoj seti s skrytymi nejronami dlya prognozirovaniya potrebnosti v kriticheskih zapasnyh chastyah //Akademicheskaya publicistika. 2021. №3.
8. Bespalova S.V., Romanchuk S.M., Ermolenko T.V., Bondarenko V.I. Postroenie predskazatel'nyh modelej parametrov davleniya vody v vodoraspredelitel'nyh setyah s pomoshch'yu metodov mashinnogo obucheniya // Problemy iskusstvennogo intellekta. 2019. №2 (13).
9. Sazont'ev V. V. Prognozirovanie cen na uslugi i tovary s ispol'zovaniem nejronnyh setej/ Pod obshchej redakciej: Tihonov A. N., Azarov V. N., Aristova U. V., Karasev M. V., Kulagin V. P., Leohin YU. L., L'vov B. G., Titkova N. S.// Nauchno-tekhnicheskaya konferenciya studentov, aspirantov i molodyh specialistov NIU VSHE. Materialy konferencii/ M. : MIEM NIU VSHE, 2014. S. 84-85.
10. Zyus'ko K.D. Prognoz sprosa na tovar s pomoshch'yu nejronnyh setej v usloviyah menyayushchejsya razmernosti vhodnyh dannyh // Ekonomika i kachestvo sistem svyazi. 2020. №1
11. Ruban O. I. Ispol'zovanie tekhnologii nejrosetej v povsednevnosti [Tekst] / O.I. Ruban // Letnyaya shkola po iskusstvennomu intellektu 2019 / Kafedra sistemnyh issledovanij MFTI, Institut problem iskusstvennogo intellekta FIC IU RAN, Rossijskaya associaciya iskusstvennogo intellekta. – 4-7 iyulya 2019 g. – Rossiya, kampus MFTI.
12. Stupak, A. A. Upravlenie zapasami s ispol'zovaniem nejronnyh setej / A. A. Stupak // Upravlenie investiciyami i innovaciyami. – 2017. – № 3. – S. 95-103. – DOI 10.14529/iimj170312.
13. Butor, L. V. Primenenie iskusstvennyh nejronnyh setej dlya prognozirovaniya zakupok = Application of artificial neural networks for procurement forecasting / L. V. Butor // Inzhenernaya ekonomika [Elektronnyj resurs] : sbornik materialov mezhdunarodnoj nauchno-tekhnicheskoj konferencii professorsko-prepodavatel'skogo sostava v ramkah 20-j Mezhdunarodnoj nauchno-tekhnicheskoj konferencii «Nauka – obrazovaniyu, proizvodstvu, ekonomike», 26-28 aprelya 2022 / Belorusskij nacional'nyj tekhnicheskij universitet, Mashinostroitel'nyj fakul'tet ; redkol.: A. V. Plyasunkov, T. A. Sahnovich ; sost. A. V. Plyasunkov. – Minsk : BNTU, 2022. – S. 12-15.
14. Balavnev, D. A. Ispol'zovanie nejronnyh setej v zadache prognozirovaniya zakupok tovarov / D. A. Balavnev, M. L. Kindulov, B. R. Gorelov, T. O. SHergin. // Molodoj uchenyj. — 2020. — № 27 (317). — S. 30-32.
15. T. Vasyaeva, Stock Prices Dynamics Forecasting with Recurrent Neural Networks [Tekst] / T. Vasyaeva, T. Martynenko, S. Khmilovyi, N. Andrievskaya // Otkrytye semanticheskie tekhnologii proektirovaniya intellektual'nyh sistem. – 2020. – No 4. – P. 277-282.
16. Stock prices forecasting with LSTM networks. Vasyaeva T., Martynenko T., Khmilovyi S., Andrievskaya N. Communications in Computer and Information Science. 2019. T. 1093. S. 59-69.
17. Vozmozhnosti i nedostatki ispol'zovaniya skol'zyashchej srednej pri vyrabotke prognoznyh reshenij // Prioritetnye nauchnye napravleniya: ot teorii k praktike. 2015. №19.
18. Trufanova T.V. Sposoby prognozirovaniya kursa valyut na osnove modelej eksponencial'nogo sglazhivaniya i Hol'ta // T.V. Trufanova, K.D. Neshchemenko / Vestnik Amurskogo gosudarstvennogo universiteta. Seriya: Estestvennye i ekonomicheskie nauki. 2019. №87.
19. Mashinnoe obuchenie dlya nachinayushchih: algoritm sluchajnogo lesa (Random Forest) [Elektronnyj resurs] – URL: https://clck.ru/335YFV// (data obrashcheniya: 19.05.2023).
20. Metod blizhajshih sosedej (kNN) [Elektronnyj resurs] – URL: https://clck.ru/34YodU// (data obrashcheniya: 19.05.2023).
21. Tipy nejronnyh setej. Princip ih raboty i sfera primeneniya [Elektronnyj resurs] – URL: https://otus.ru/nest/post/1263 // (data obrashcheniya: 19.05.2023).
22. Pustynnyj YA.N. Reshenie problemy ischezayushchego gradienta s pomoshch'yu nejronnyh setej dolgoj kratkosrochnoj pamyati // Innovacii i investicii. 2020. №2.
23. Turunceva Marina YUr'evna Ocenka kachestva prognozov: prostejshie metody // Rossijskoe predprinimatel'stvo. 2011. №8-1.
24. Koefficient determinacii (Coefficient of determination) [Elektronnyj resurs] – URL: https://wiki.loginom.ru/articles/coefficient-of-determination.html // (data obrashcheniya: 19.05.2023).
25. Kinyakin V.N. Nekotorye predosterezheniya po proverke kachestva modeli regressii s pomoshch'yu koefficienta determinacii // V.N. Kinyakin, YU.S. Milevskaya / Vestnik Moskovskogo universiteta MVD Rossii. 2014. №8.
26. SHpargalka po raznovidnostyam nejronnyh setej. CHast' pervaya. Elementarnye konfiguracii [Elektronnyj resurs] – URL: https://tproger.ru/translations/neural-network-zoo-1 // (data obrashcheniya: 20.05.2023).

Issues: 4(31)'2023
Section: Math modeling
Cite: Andrievskaya, N. APPLICATION OF STATISTICAL METHODS, CLUSTER ANALYSIS AND NEURAL NETWORK TECHNOLOGIES IN FORECASTING PROCUREMENT PRICES FOR MEDICINES // N. Andrievskaya, T. Martynenko, T. Vasyaeva // Проблемы искусственного интеллекта. - 2023. № 4 (31). - 41-55. - http://search.rads-doi.org/project/14374/object/210541 doi: 10.34757/2413-7383.2023.31.4.005

back to issues 4(31)'2023