Upgrade to Pro — share decks privately, control downloads, hide ads and more …

ML for Marketing

ML for Marketing

We built ML models to optimize revenue through marketing by predicting whether there will be coupon redemption in a transaction or not.

Shanelle Recheta

March 18, 2021
Tweet

More Decks by Shanelle Recheta

Other Decks in Programming

Transcript

  1. Coupon
    Redemption
    team.fit()

    View full-size slide

  2. Grocery
    at your fingertips

    View full-size slide

  3. 1,116
    100
    out of
    coupons redeemed

    View full-size slide

  4. What will work?
    Who to target in their specific campaigns?
    What is working?
    Which campaigns are likely to succeed?
    What has worked?
    Which coupons should be revisited?

    View full-size slide

  5. Data-driven Marketing
    Increase customer loyalty
    Increase customer
    engagement
    Increase profit

    View full-size slide

  6. Customer-first Analytics
    ● Profiling the customers through
    K-means Clustering
    ● Observe customer behavior
    through Aggregation of features
    ● Comparing the performance
    of campaigns through
    descriptive stats

    View full-size slide

  7. Opportunity to Market: Purchasing Power
    Get median purchase duration
    between customers
    Recommend a coupon at about the
    same time they will be purchasing again
    Make the product stickier

    View full-size slide

  8. Underlying Magic: Feature Extraction
    Customer-centric
    variables
    Research-based
    (domain knowledge)
    Time-centric and
    Categorical
    variables
    ML-first EDA
    (getting high variance trees
    from Random Forest)

    View full-size slide

  9. Underlying Magic: Running K-means TWICE

    View full-size slide

  10. Underlying Magic
    Strong Positive Correlation
    ● brand vs item type
    ○ e.g. Packaged Meat
    ● brand vs campaign release date
    ○ Day of week
    ○ Month (seasonality)

    View full-size slide

  11. Challenges Encountered
    ● Integrating all datasets
    ● Feature Extraction
    ○ Effectively encoding categorical columns
    ○ Clustering and extracting features from what the trees say have
    highest feature importance
    ● Dealing with missing variables
    ○ KNN impute
    ● High memory usage: Large number of rows = long processing time
    ○ Used SQL for queries

    View full-size slide

  12. Challenges Encountered
    ● Models tested: Random Forest, XGBoost, fast.ai
    ○ bootstrapped significantly: bagging principle
    ○ Fast iteration: we didn’t have a model that went through the entire dataset
    ○ All models were bootstrapped instances that were averaged out
    ○ fast.ai to ensure trees weren’t correlated to maximize the feature insights
    acquired
    ● Overfitting
    ○ L1 regularization does the trick

    View full-size slide

  13. Insights and Recommendations
    Factors affecting Success of Campaign
    ● Day of the week that promos come out have relatively significant effect
    purchases and campaign came in
    ● There are shoppers that shop heavily on specific days
    ● Customers buy the same way
    ● Brand type released on certain dates (start of week, seasonality)
    ● Coupons that can be used for many items are redeemed more often

    View full-size slide

  14. Future Work
    ● Integrate Brand-level Categorical Variables
    ● Product Category Clustering: Looking at Price Sensitivities across Brands and
    Categories
    ● Item code - Categories - Brand: Mapping and Analysis
    ● Matrix Factorization for Coupon Recommendation
    ● Collect data on profit per item (sales =/= profit) to effectively measure
    profitability of the marketing campaign

    View full-size slide

  15. team.fit()
    Alec Wang
    Tech Maven
    Daryl Collantes
    Designer
    Shane Recheta
    Project Leader

    View full-size slide

  16. Thank you!
    team.fit()

    View full-size slide