[dipl] Perustieteiden korkeakoulu / SCI

Permanent URI for this collectionhttps://aaltodoc.aalto.fi/handle/123456789/21

Browse

Browsing [dipl] Perustieteiden korkeakoulu / SCI by Author "Aalto, Henrik"

Filter results by typing the first few letters
Now showing 1 - 1 of 1
  • Competition-Based Dynamic Pricing in E-Commerce
    (2019-12-17) Aalto, Henrik
     Perustieteiden korkeakoulu | Master's thesis
    E-commerce is a fascinating field of retail. It offers numerous advantages for retailers starting from widely reachable customers, easily changeable assortments, and reduced fixed costs. On the other hand, e-commerce accelerates competition. For a consumer it is merely a matter of some clicks to switch from one online store to another offering the same item with faster shipping or lower price. The goal of this study is to find and evaluate a method to dynamically reprice durable goods over an infinite horizon in an online store based on competitor prices for the same products. To provide support for the method, we first model the daily sales quantities with a zero-inflated binomial regression. Then, we build a myopically optimal pricing method on top of the demand model. The performance of the model is assessed by simulations with two different scenarios, one assuming competitors would not react and another assuming one of them starts a price war. In both the scenarios, our pricing method is able to perform well with up to 20 percent increase in gross margin compared to current pricing. Last, we conduct a case study by repricing a group of products in an online store for a month with our method. Due to large variances in sales and a small test group, no statistically sound conclusions can be made. However, the performance of our method is roughly equal to the current pricing policies. Thus, one could conduct a larger and longer test to gain more information. The key findings in our study are as follows. First, even rather simple pricing methods should outperform any static pricing rules. Second, having competitor price information available in e-commerce is crucial as the difference to competitors matters more than the price point itself. Third, detecting changes from the sales of slowly moving goods would require huge sample sizes and thus performances of pricing methods should be assessed with products with higher demands.