Thursday, August 25, 2016

trying to embed pdf

Introductory text or abstract, then
to read more:
Here is the doc

so the steps are:
upload pdf to drive
change settings to public
copy the link
then in blogger, new post, compose, insert link and whatever text
then publish, it will appear on Google+.

Check: as a reader, click on link, it takes you to the pdf on owner's google+ or googleDocs whatever, click yet again on that and it leads to to full pdf.

If this is what Google does with simple pdf publication, how can we trust them to design a self-driveling car?

Sunday, June 7, 2015

Video CPM as a Function of Demand - Complete

Video CPM as a function of Demand

Experiment description and Analysis

13 biggest client tactics representing about 9% of total video revenue were duplicated with all prior restrictions (geo, site, device etc.), additionally restricted to Tier I-III inventory and budget-density tested at 1X, 2X, 6X and 12X daily budget on 25, 12, 4 and 2 buckets respectively.

For each of these budget points we have the spend, cost and impressions in the TierI-III inventory.

From other sources (Roni's presentation) we know that about 15% of all our impressions (50% of all avails and 20% of cost) are in Tier I-III,

so for all the video tactics which weren't restricted to TierI-III as part of this test, we uniformly apportioned 20% of spend and cost (assuming margin was same) and 15% impressions in the tested user buckets to TierI-III inventory.

The above spend cost and impressions were added to those for the tested tactics, 

and CPM vs daily cost was plotted and fitted to a power law. 

Why a power law? Because cost (CPM) elasticity of demand (total cost) is the ratio of the logarithmic derivatives, which is just the exponent in a power law. 

dailySpend = AnnualSpend/365





dailyCost = (1-margin)*dailySpend





actualDailyCost = (spendFraction + (1-spendFraction)*costFraction) * dailyCost






Cost Based CPM from fit to elasticity curve evaluated at actualDailyCost
Revenue CPM = CostCPM/(1-margin)








Effect of Geo, Site, Device and DealID restrictions

DealID restrictions were in effect for all 13 line_items, so effect cannot be measured.

All restrictions data:
As one can see from the following plots, none of the other three restrictions which were variously present/absent in the tested line_items show any significant effect on either the coefficient (CPM at $10K, multiplicative effect) or the elasticity (exponent, additive effect).



Wednesday, June 3, 2015

ClickMePushYou

The Puzzle

If you click on me...

I will disappear.

Try clicking me away!

No, dooon't!

How did you do?

Your score = 6 - (number of clicks + page_refreshes)

Tuesday, June 2, 2015

Player size restricted Video CPM as a function of Demand

Player size restricted Video CPM as a function of Demand

Experiment description and Analysis

Biggest client tactics representing about 9% of total video revenue were duplicated with all prior restrictions (geo, site, device etc.), additionally restricted to Player size > 400 X 300 and budget-density tested at 1X, 2X, 6X and 12X daily budget on 25, 12, 4 and 2 buckets respectively. For each of these budget points we have the spend, cost and impressions in the player size inventory.

We are clearly having trouble delivering at scale for the higher budget density - we are delivering only about 35%. For example, to hit the actual budget density points, every tactic in a line item (targeting different numbers of user buckets) should have had the same cost, yet on 5/19/15 the cost in "2 buckets" is only 129 instead of 379. Hence, while the goal was to explore a range  12X the current total video revenue, in practice we've only been able to get to about 4X. 

From querying our database


we know that about 35% of all our impressions  and 35% of video cost are for player size > 400X300, so for all the video tactics which weren't restricted by player size as part of this test, we uniformly apportioned 35% of spend and cost (assuming margin was same) and 35% impressions in the tested user buckets to player size restricted inventory.


The above spend cost and impressions were added to those for the tested tactics, 


and CPM vs daily cost was plotted and fitted to a power law. 


Why a power law? Because cost (CPM) elasticity of demand (total cost) is the ratio of the logarithmic derivatives, which is just the exponent in a power law. 

The Calculator





dailyCost = (1-margin)*dailySpend






actualDailyCost = (spendFraction + (1-spendFraction)*costFraction) * dailyCost







Cost Based CPM from fit to elasticity curve evaluated at actualDailyCost
Revenue CPM = CostCPM/(1-margin)








Monday, April 27, 2015

Annual Video spend to Cost CPM calculator

Video CPM as a function of Demand

Experiment description and Analysis

13 biggest client tactics representing about 9% of total video revenue were duplicated with all prior restrictions (geo, site, device etc.), additionally restricted to Tier I-III inventory and budget-density tested at 1X, 2X, 6X and 12X daily budget on 25, 12, 4 and 2 buckets respectively. For each of these budget points we have the spend, cost and impressions in the TierI-III inventory.

From other sources (Atul's presentation) we know that about 15% of all our impressions (50% of all avails) are in Tier I-III, so for all the video tactics which weren't restricted to TierI-III as part of this test, we uniformly apportioned 20% of spend and cost (assuming margin was same) and 15% impressions in the tested user buckets to TierI-III inventory.

The above spend cost and impressions were added to those for the tested tactics, 

and CPM vs daily cost was plotted and fitted to a power law. 

Why a power law? Because cost (CPM) elasticity of demand (total cost) is the ratio of the logarithmic derivatives, which is just the exponent in a power law. 

How do I put in formulas? dailySpend = AnnualSpend/365





dailyCost = (1-margin)*dailySpend






actualDailyCost = (spendFraction + (1-spendFraction)*costFraction) * dailyCost







Cost Based CPM from fit to elasticity curve evaluated at actualDailyCost
Revenue CPM = CostCPM/(1-margin)








Effect of Geo, Site, Device and DealID restrictions

DealID restrictions were in effect for all 13 line_items, so effect cannot be measured.

All restrictions data:
As one can see from the following plots, none of the other three restrictions which were variously present/absent in the tested line_items show any significant effect on either the coefficient (CPM at $10K, multiplicative effect) or the elasticity (exponent, additive effect).