3 Common Mistakes When Looking At Freemium Metrics

GIAF
3 COMMON MISTAKES WHEN
         LOOKING AT FREEMIUM
               METRICS



Sunday, 3 February 13
INTRODUCTION



    •   Product Lead at NaturalMotion

    •   Previously worked on:




                        stan.beremski@naturalmotion.com

Sunday, 3 February 13
OVERVIEW OF FREEMIUM
                         GAMES



Sunday, 3 February 13
THE FREEMIUM MODEL




                                                App Store



                                                  Engage



                                                  Retain




                                             Monetize + Invite



Sunday, 3 February 13
Good metrics give you insight into conversion at each stage of
                                          the model



                                           App Store



                                             Engage




                                             Retain



                                        Monetise + Invite



                            Good metrics have explanatory powers


Sunday, 3 February 13
MISTAKE #1

                     NOT FOCUSING ON
                    EXPLANATORY METRICS



Sunday, 3 February 13
Vanity                                     Explanatory



 •    Users                      •   Total Revenue / Total Users   • Cohort segmentation
 •    Page Views                 •   Session per player / day        • Retention
 •    Daily Revenue              •   Invites sent / player           • LTV
 •    Total Mins of Play         •   Invites accepted / Invite       • Sessions pp / day
 •    Total Sessions             •   ARPDAU
                                 •   DAU/MAU                       • Behavioural segmentation
                                                                     • Whales vs Free
                                                                     • Single player vs Multi

                                                                   • Funnels
                                                                     • Tutorial / Quest
                                                                     • Virality funnel

          Counts                               Ratios                     Segmented
                                                                            Ratios

Sunday, 3 February 13
MISTAKE #2

                NOT CONTROLLING FOR
                     VARIABLES



Sunday, 3 February 13
You have just released an update to your game and you take a look at the
 metrics to gauge success...


  • Did this update improve monetisation?




 • How long did it take to us get a conclusive answer?

 (Data is fictional)

Sunday, 3 February 13
There is a problem if you only look at New Users, Revenue and ARPDAU to
 gauge the success of an update...




                          (Data is fictional)
 Problem: Metrics can be affected by uncontrolled variables
      • In our fictional game players spend 90% of their LTV within 7 days of first playing the app
      • An large influx of new players will cause a revenue spike even if the app remains unchanged
   Solution: Look at metrics which isolate what you are interested in and control
   for other variables (in this case the player’s lifecycle within the app)

Sunday, 3 February 13
The solution is to look at player LTV at specific points in the player’s lifecycle


                        Total Revenue from cohort
                                                                   Player LTV N days into
        LTV =                                        Day N LTV =
                                                                   the lifetime of a cohort
                        Total # Player of a cohort




                                (Data is fictional)



Sunday, 3 February 13
MISTAKE #3

                        NOT LOOKING AT THE
                         DISTRIBUTION OF
                         UNDERLYING DATA

Sunday, 3 February 13
We often look at averaged data.




                        {1,2,3,3,3,4,4,5,10}
                        Mean = 3.89
                        Median = 3
                        Mode = 3




Sunday, 3 February 13
Power-law distribution are common in freemium games




                             Represents $65,000 revenue from110,000 players




             Max: $624
             Min: $0                                                          (Data is fictional)
             Mean: $0.57
             Median: $0
             Mode: $0
             Std Dev: 7.12
             % Payers: 5%


Sunday, 3 February 13
But statistics can be misleading...




                    Property                                                       Value
                    Mean	
  of	
  x	
  in	
  each	
  case                          9	
  (exact)
                    Variance	
  of	
  x	
  in	
  each	
  case                      11	
  (exact)
                    Mean	
  of	
  y	
  in	
  each	
  case                          7.50	
  (to	
  2	
  decimal	
  places)
                    Variance	
  of	
  y	
  in	
  each	
  case                      4.122	
  or	
  4.127	
  (to	
  3	
  decimal	
  places)
                    CorrelaAon	
  between	
  x	
  and	
  y	
  in	
  each	
  case   0.816	
  (to	
  3	
  decimal	
  places)
                    Linear	
  regression	
  line	
  in	
  each	
  case             y	
  =	
  3.00	
  +	
  0.500x	
  (to	
  2	
  and	
  3	
  decimal	
  places,	
  respecAvely)



Sunday, 3 February 13
1 of 15

More Related Content

3 Common Mistakes When Looking At Freemium Metrics

  • 1. 3 COMMON MISTAKES WHEN LOOKING AT FREEMIUM METRICS Sunday, 3 February 13
  • 2. INTRODUCTION • Product Lead at NaturalMotion • Previously worked on: stan.beremski@naturalmotion.com Sunday, 3 February 13
  • 3. OVERVIEW OF FREEMIUM GAMES Sunday, 3 February 13
  • 4. THE FREEMIUM MODEL App Store Engage Retain Monetize + Invite Sunday, 3 February 13
  • 5. Good metrics give you insight into conversion at each stage of the model App Store Engage Retain Monetise + Invite Good metrics have explanatory powers Sunday, 3 February 13
  • 6. MISTAKE #1 NOT FOCUSING ON EXPLANATORY METRICS Sunday, 3 February 13
  • 7. Vanity Explanatory • Users • Total Revenue / Total Users • Cohort segmentation • Page Views • Session per player / day • Retention • Daily Revenue • Invites sent / player • LTV • Total Mins of Play • Invites accepted / Invite • Sessions pp / day • Total Sessions • ARPDAU • DAU/MAU • Behavioural segmentation • Whales vs Free • Single player vs Multi • Funnels • Tutorial / Quest • Virality funnel Counts Ratios Segmented Ratios Sunday, 3 February 13
  • 8. MISTAKE #2 NOT CONTROLLING FOR VARIABLES Sunday, 3 February 13
  • 9. You have just released an update to your game and you take a look at the metrics to gauge success... • Did this update improve monetisation? • How long did it take to us get a conclusive answer? (Data is fictional) Sunday, 3 February 13
  • 10. There is a problem if you only look at New Users, Revenue and ARPDAU to gauge the success of an update... (Data is fictional) Problem: Metrics can be affected by uncontrolled variables • In our fictional game players spend 90% of their LTV within 7 days of first playing the app • An large influx of new players will cause a revenue spike even if the app remains unchanged Solution: Look at metrics which isolate what you are interested in and control for other variables (in this case the player’s lifecycle within the app) Sunday, 3 February 13
  • 11. The solution is to look at player LTV at specific points in the player’s lifecycle Total Revenue from cohort Player LTV N days into LTV = Day N LTV = the lifetime of a cohort Total # Player of a cohort (Data is fictional) Sunday, 3 February 13
  • 12. MISTAKE #3 NOT LOOKING AT THE DISTRIBUTION OF UNDERLYING DATA Sunday, 3 February 13
  • 13. We often look at averaged data. {1,2,3,3,3,4,4,5,10} Mean = 3.89 Median = 3 Mode = 3 Sunday, 3 February 13
  • 14. Power-law distribution are common in freemium games Represents $65,000 revenue from110,000 players Max: $624 Min: $0 (Data is fictional) Mean: $0.57 Median: $0 Mode: $0 Std Dev: 7.12 % Payers: 5% Sunday, 3 February 13
  • 15. But statistics can be misleading... Property Value Mean  of  x  in  each  case 9  (exact) Variance  of  x  in  each  case 11  (exact) Mean  of  y  in  each  case 7.50  (to  2  decimal  places) Variance  of  y  in  each  case 4.122  or  4.127  (to  3  decimal  places) CorrelaAon  between  x  and  y  in  each  case 0.816  (to  3  decimal  places) Linear  regression  line  in  each  case y  =  3.00  +  0.500x  (to  2  and  3  decimal  places,  respecAvely) Sunday, 3 February 13