The bankruptcy of Russian companies in the existing environment has become rather common. Determination of bankruptcy risk factors allows predicting the prospects for business development. The authors set the task to determine the relative influenceof individual financial and non-financial factors on the probability of a company’s bankruptcy. To study risk factors, the authors analyzed 3184 large Russian companies (with revenues of more than 2 billion rubles per year and more than 250 employees) of various industries operating from 2009 to 2020. The total number of observations is 38,208. For analysis, 30 factors were selected and divided into five groups: profitability, liquidity, turnover, financial stability and general (non-financial) factors. For the study, one of the machine learning methods was used – the random forest method. The sample consists of companies from seven industries, including manufacturing, retail, construction, electric power, mining, agricultural production, and water supply, as well as other industries, which include companies in education, healthcare, agriculture, and hospitality. The analysis was carried out both in aggregate for the entire sample without being distributed by industry, and for samples distributed by manufacturing, retail, and service industries. In the sample as a whole, the tested model in 86% of cases correctly predicted the possibility of a company going bankrupt for the period under review. This result confirmed that machine learning methods (in particular, the random forest algorithm) are highly effective in solving the problem of bankruptcy prediction for a company. Based on the data obtained, the paper concludes that profitability factors have the most significant impact on the probability of bankruptcy for manufacturing and retail companies. For service companies, it is financial stability factors. Solving the problem of determining the bankruptcy risk factors of Russian companies will ensure a reduction in the number of bankrupt enterprises, which, in turn, will contribute to the recovery and development of the national economy.