1 / 18

Modeling Seller Listing Strategies

Motivation: Modeling eBay Sellers' Activities. A majority of eBay sellers are individuals or small sale operations (heterogeneous)eBay platform provides a wide variety of options for listing for-sale item . 2. Goal. Construct a behavior model:captures seller listing activitiesincorporates histori

sterling
Download Presentation

Modeling Seller Listing Strategies

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


    1. Modeling Seller Listing Strategies Quang Duong University of Michigan Neel Sundaresan Nish Parikh Zeqiang Shen eBay Research Labs 1

    2. Motivation: Modeling eBay Sellers’ Activities A majority of eBay sellers are individuals or small sale operations (heterogeneous) eBay platform provides a wide variety of options for listing for-sale item 2 When looking at the sellers on eBay, we observe that unlike others. Interesting problems. Unlike thebuyer side of market places where there has been a lot of studies on buyer experience and behavior, online sellers side has not been attracting much attention. When looking at the sellers on eBay, we observe that unlike others. Interesting problems. Unlike thebuyer side of market places where there has been a lot of studies on buyer experience and behavior, online sellers side has not been attracting much attention.

    3. Goal Construct a behavior model: captures seller listing activities incorporates historical data and sale competitions across different product groups/markets Domain: eBay 3

    4. Applications Identify and foster good (listing) practices: advise and suggest good practices to average sellers. Assist market design For example, eBay platform changes: how changes impact sellers’ strategies 4

    5. Related work Benefits of “Buy it now” [Anderson et al. 2004] Clustering sellers [Pereira et al. 2009] Statistical models of agent’ listing strategies [Anderson et al. 2007] Our model incorporates: dynamic elements interactions among sellers 5 Although there have been….. Main point: but the lack: do not incorporate their interactions/ do not incorporate Although there have been….. Main point: but the lack: do not incorporate their interactions/ do not incorporate

    6. Overview 6

    7. Data Processing Product Clustering: Need to group listings of the same product Use a catalog: match each listing to a product in the catalog Match product name and brand Count the number of matched words between product’s catalog description and listing’s title 7 -same product: for example, silver nano ipod is the same as silver nano -same product: for example, silver nano ipod is the same as silver nano

    8. Data Processing (cont.) Data summarization: Assume sellers adjust their listings in 1-week intervals. For each 1-week interval, each product and each seller: Average price Relative average price Number of listings (Percentage of free-shipping listings) (Percentage of featured listings) Product category: seller adopt the same strategy for products in the same product category For example, product: black/silver iPhones; product category: iPhone 8 Product category: not only assuming that the same strategy over time, but for the same product category -- Explain feature listing…Product category: not only assuming that the same strategy over time, but for the same product category -- Explain feature listing…

    9. Markov Model: State and Action Representations 9 Assumptions: Markov property: only dependent on the immediate state (relaxed later)

    10. State-Action Model 10 QUESTIONS: Why incorporating past action? May not be markovian why not incorporating more information? QUESTIONS: Why incorporating past action? May not be markovian why not incorporating more information?

    11. Model Learning and Evaluation Learning Given training data D, learn model M’s transition: Pr(action|state) Each data point is computed over all listings for one product (in one particular product category) in a week for a particular seller. Evaluation Given testing data D’, compute the log likelihood of D’ with M: L(M)=avg(log(Pr(action|state)) Given two models M1 and M2 L(M1,M2)= L(M1) / L(M2) (smaller than 1 means M1 is better than M2) Final measure: 1 - L(M1,M2) ? How much M1 is better than M2. 11 Explain the measuresExplain the measures

    12. Empirical Study Examine activities of the best performing seller (S0), second best seller (S1), and an average seller (S2). 3 months worth of data (2/3 for training, 1/3 for testing) Three product categories: charger, battery and screen protector (for iPhones) 12 How to define seller performances? OBJECTIVE: what empirical study?How to define seller performances? OBJECTIVE: what empirical study?

    13. Comparison with the Baseline Semi-uniform Model Semi-uniform model (M0): Pr(do-nothing|state) is 50% other actions are randomly uniformly chosen. Results for top seller S0 and second-best S1 Sellers do adopt strategies for their listings 13

    14. Comparison with the History-independent Model History-independent model (Mh): does not incorporate the last action Results for top seller S0 There are benefits of including information about last actions in capturing listing strategies 14

    15. Cross-product Analysis For seller S0, across different product categories: M1 | D’1(D’2): model trained on product category 1’s data, tested on product category 1(2)’s data The top seller appears to execute relatively different strategies for different product categories. 15

    16. Cross-seller Analysis Compare different sellers’ strategies for the same product categories: The best and second-best sellers have similar strategies in the two product categories: charger and battery, but different strategies for the screen protector. The top seller and the average seller diverge significantly for both charger and screen protector 16

    17. Sale-through Rate and Average Revenue Analysis We want to compare the effectiveness of seller 0 and seller 2’s strategies: Sale-through rate Average revenue Challenge: listings created at time t may affect sales of previously created listings Solution: Listings sold < 2 weeks after posted are counted as the original action’s effect Listing sold >= 2 weeks are counted as the newest action’s effect 17

    18. Conclusions Contributions: Introduce a model that captures sellers’ listing activities, accommodates probabilistic reasoning about their behavior, and enables the inclusion of historical information demonstrate the application of our model in comparing listing strategies from different sellers across different product categories 18

More Related