Selecting an Enterprise Development Strategy Using Machine Learning Methods
Mikhail Leizerovich Krichevsky1, Julia Anatolevna Martynova2

1Kavin. R, Department of EEE, Sri Krishna College of Engineering and Technology, Coimbatore (Tamil Nadu), India.
2Elamcheren. S, Department of EEE, Sri Krishna College of Engineering and Technology, Coimbatore (Tamil Nadu), India.
3Dr. S. Sheebarani Gnanamalar, Department of EEE, Sri Krishna College of Engineering and Technology, Coimbatore (Tamil Nadu), India.

Manuscript received on 18 April 2019 | Revised Manuscript received on 25 April 2019 | Manuscript published on 30 April 2019 | PP: 1091-1097 | Volume-8 Issue-4, April 2019 | Retrieval Number: D6462048419/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: It is particularly difficult to choose from enterprise strategies amid a changing economic situation, inaccurate definitions of variables affecting the company’s actions, and incomplete information about the competitors’ behavior. It is preferable to use methods that are part of machine learning (ML) when choosing a strategy in such a situation. The purpose of the study is to develop a method for selecting a strategy using ML instruments, which should include ways to select the most important indicators of an enterprise, estimate a market share of an enterprise among competitors, and test the efficiency of the created method on simulated or real data. Neural and fuzzy systems are the most suitable ML instruments for solving the problem. The Statistica software package implements a mechanism for selecting an appropriate enterprise strategy using the neural network (NN) system. A trained NN as a perceptron allows to choose a procedure of the organization’s actions that suits the current situation best, depending on a set of selected variables that influence the strategy. A hybrid neuro-fuzzy system (NFS) like ANFIS, which is a combination of NNs and fuzzy logic (FL), is used to estimate the market share of the company. It is advisable to reduce the number of input variables when working with this module, which is done using the Feature Selection tool that allows to rank parameters and select the most significant ones.
Keywords: Enterprise Strategy, Machine Learning, Feature Selection, Strategy Selection, Market Share Estimation.

Scope of the Article: Machine Learning