Design/Pseudo Code for Redis-based Ecommerce Recommendation App

  • État: Closed
  • Prix: $440
  • Propositions reçues: 1
  • Gagnant: rifatsikder333

Résumé de concours

I am fleshing out an app for making product recommendations for an e-commerce site. I have a rough outline of the architecture but I am looking to define microservices and the Redis services that will implement them. Delivery is not code but pseudo code that shows how Redis will be used in various ways in stages of the app. The app can refer to other non-Redis services such as Spark or anything else.

Compétences recommandées

Commentaire de l'employeur

“Rifatsikder333 really understood my true needs and helped meet them.”

Image de profil evolvedmediavw, United States.

Meilleures propositions de ce concours

Afficher plus de propositions

Tableau de clarification publique

  • evolvedmediavw
    Titulaire du concours
    • il y a 1 an

    Part 3:

    #For each domain we have a machine learning model that will recommend the most suitable items
    #according to the users feature vector. The models are trained on Spark and stored on Redis ML.
    for domain in domains:
    #for each item class of the domain get a score from the random forest classifier
    for item in domain.items:
    domain.itemScores[item] = RedisRandomForestClassify(forestId = "domain:item", featureVector)

    #sort the classification results and get the top results to render recommendations
    results[domain] = domain.itemScores.sort()[0:n_items]

    • il y a 1 an
  • evolvedmediavw
    Titulaire du concours
    • il y a 1 an

    Part 2:

    #We should have a domain object which will contains the items and attributes of the domain.
    #The domains will be stored in a dictionary. e.g.:
    #domains[news] = ("World", "U.S.", "Politics", "Business", "Tech", "Science", "Health", "Sports", "Arts", "Style", "Food", "Travel")
    #domains[ads] = ("Nissan", "pertasperlite", "panachemodels", "TransMilenio", "hermaspuspito", "Jeep", "CocaCola", "Konami", "Samsung", "BWWings", "WWENetwork", "givenchy")
    #The domain items will be loaded from a Redis set:

    domains[news] = redis.smembers("domain:news:items")
    domains[ads] = redis.smembers("domain:ads:items")

    • il y a 1 an
  • evolvedmediavw
    Titulaire du concours
    • il y a 1 an

    Here is the sort of code I am looking for:

    MS: Real Time Recommendation

    #Load the user's feature vector from Redis. The feature vector is stored as a redis hash.
    #an example of a feature vector: ("age:31", "sex:male", "food_1:pizza", "food_2:sriracha", "last_url:news.ycombinator.com")
    featureVector = redis.hget(uid:features)

    • il y a 1 an
  • anmsaiful
    anmsaiful
    • il y a 1 an

    I have experience in both design and development. But I am not clear about your project specification. Feel free to initiate a chat to discuss about the project in detailed. Hope I can come up with a working solution. :-)

    • il y a 1 an
    1. evolvedmediavw
      Titulaire du concours
      • il y a 1 an

      Did you see the document? What I'm looking for is to write pseudo code that shows how a set of microservices would work, invoking Redis capabiliites, to implement a generic e-commerce recommendation/personalization engine.

      • il y a 1 an
    2. evolvedmediavw
      Titulaire du concours
      • il y a 1 an

      The deliverable would be Pseudo code for the microservices defined on the document associated with this project. The idea is to define what Redis services would help implement each microservice.

      • il y a 1 an

Montrer plus de commentaires

Comment commencez des concours

  • Publiez votre concours

    Publiez votre concours Rapide et facile

  • Obtenez des tonnes de propositions

    Obtenez des tonnes de propositions De partout dans le monde

  • Attribuez la meilleure proposition

    Attribuez la meilleure proposition Télécharger les fichiers - Facile !

Publier un concours maintenant ou rejoignez-nous maintenant !