Avito Product Analytics Meetup December 9th: Announcement

    Companies are collecting more and more information about users. But it is not enough to get it; it is important to understand what kind of data and how will be used. We invite product and data analysts to the Avito Product Analytics Meetup. Let's talk about how to work with the data warehouse and scale it for high loads, about personalizing the site for users based on the customer journey map and about measuring user satisfaction. Under the cut - abstracts, links to registration and live broadcasting.



    Reports


    Analytical storage Avito.ru - from large to very large data. Artyom Danilov (Avito)


    imageAt first glance, designing a data warehouse is a typical task: gather requirements, build a data model, and implement ETL. However, the avalanche-like growth in the volume of data and its complexity can easily disrupt the performance of the storage. The report shows:
    - how, following the expansion of the business, Avito storage grew up to 76 TB in a few years;
    - Where does the company get big data from?
    - what are the basic principles of analytics;
    - how Avito.ru storage evolved.
    Particular attention is paid to the answer to the question why following the restrictions of the sixth normal form (Anchor Modeling) helps to quickly expand the storage, effectively scale the load in the environment of MPP DBMS and develop in microservices.


    Personalization of the site for the user based on customer journey map. Alexey Chernobrovov


    imageFrom the report you will learn about what a customer journey map (CJM) is. The main approaches to the automated allocation of user behavior patterns using modern machine learning methods will be described. Alexey will talk about building personalization based on CJM and choosing the right metrics to evaluate product improvement. As examples, the application of a large bank, the site of a well-known car dealer and a large online store will be used.


    Avito NPS: The voice of users in product development. Danila Lenkov (Avito)


    imageIn any large company, they know that the secret to a successful business and a brighter future is customer happiness. But measuring it and learning how to work to increase the level of happiness is not an easy task. All over the world they solve it with the help of customer surveys. The most successful survey technique is called the Net Promoter Score, or NPS.
    Avito is an extensive business with many business verticals. Therefore, the task of building a survey system is even more difficult than usual. The report will tell a success story about the implementation of NPS in all parts of the product and show how the large flow of votes from our users helps us make effective decisions and constantly improve.


    Features of the Avito survey system:
    - Thousands of user votes per week from all platforms: website, mobile site and applications;
    - The decision to display the desired survey option is personal for each user and is taken directly online;
    - automated pipeline for collecting results and delivering them to reports;
    - classification of text feedbacks for prioritizing decisions.


    How to increase conversion using smart sorting of the results. Case Ostrovok.ru. Evgeny Shneiderman (Ostrovok.ru)


    imageThe problem of sorting goods in the issuance list is a classic task of modern online business. In Ostrovok.ru, too, they have long been preoccupied with the issue of optimizing issuance and have done a lot of work along the way. In the report, Eugene Schneiderman will talk about the main stages in the development of the hotel sorting logic, describe the problems and errors that the team faced, as well as the conclusions that it turned out.


    • Why is optimization of the issuance order a powerful leverage for conversion growth?
    • What can be the approaches to sorting logic, what are their pros and cons?
    • Why are such solutions difficult to provide without a high-quality Big Data infrastructure?
    • How to structure a project team to provide fast iteration and improvement of a Data Science product?

    We’ll talk about all this at the Avito Product Analytics Meetup.


    Cross-product effects, or how we evaluated the contribution of the Electric Train. Ekaterina Loseva (Tutu.ru)


    imageMany companies offer the market several products at once. A case takes a special place when there is a product in the portfolio that does not directly generate revenue. How to measure its impact on sales? What benefits does the existence of this product bring to the company? In her report, Tutu.ru analyst Yekaterina Loseva will talk about the evolution of the company's approaches to calculating cross-product effects metrics using the Electric Train section as an example.


    Passwords and appearances


    Participation in the event is free, registration is required .
    Gathering of participants: 12:00
    Start of reports: 12:30
    Address: Avito office, Lesnaya 7 .
    The broadcast will be organized on the day of the event on our youtube channel AvitoTech . Subscribe to not miss anything!


    See you!


    Also popular now: