Loading...

Data-Driven Pricing Based on Demand Prediction Using Machine Learning Methods

Khosroshahi, Fatemeh Zahra | 2023

14 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 56452 (01)
  4. University: Sharif University of Technology
  5. Department: Industrial Engineering
  6. Advisor(s): Sedghi, Nafiseh
  7. Abstract:
  8. Pricing plays an important and essential role in the profit and income of companies. The importance of pricing is not only related to its role in the company's profitability, but it also changes the customer's understanding and loyalty towards the company and can create the company's reputation or destroy it. Determining the right price will increase product sales and increase customer loyalty and create a competitive advantage for the company. One of the most important and influential variables in product pricing is the amount of demand. The main challenge of companies for product pricing is the uncertainty in their demand. In order to deal with this problem, data-driven pricing is used. First, by using sales data, the amount of product demand is determined by using machine learning methods, and then the pricing of products is done based on their predicted demand. In this research, an attempt has been made to use distribution forecasting methods instead of point forecasting in order to further reduce the uncertainty of demand and increase the validity of the prices provided based on demand forecasting. First, the product demand distribution is estimated using appropriate methods, and then pricing is done based on the predicted demand distribution. To estimate the distribution, the price of other products are included as a predictor variable in the forecasting model so that the effects of substitution and complementarity between products are implicitly considered in the pricing model. A discrete optimization model is also used for pricing, which selects the appropriate price of products from among a number of candidate prices, in order to maximize the company's profit. Due to the estimation of demand distribution, this method covers more uncertainty compared to other researches conducted in this field, and the price provided based on this method is more reliable. It is also more guaranteed to be profitable. The numerical results show that the price provided by this method, compared to the price obtained through the point estimate of demand, has more validity and as a result this method will increase profitability for businesses when the level of uncertainty is high
  9. Keywords:
  10. Machine Learning ; Demand Uncertainty ; Demand Forecasting ; Pricing Based on Demand Prediction ; Data-Driven Pricing

 Digital Object List

 Bookmark

...see more