Customer Analytics, Unit Economics, SAAS, Subscriptions and Forecasting

Moats: “From Competitive advantage (Moats: Tech, scale,etc) flows good unit economics”- Josh Wolfe
Michael Mauboussin Measuring the Moat – csinvesting
Network Effects by a16z

Good collection of links from: http://www.fortunefinancialadvisors.com/blog/the-value-of-lasting-moats

Morningstar’s What Makes a Moat?

Patrick O’Shaughnessy’s interview with Pat Dorsey, who focuses his investment firm on wide moat companies:

Pat Dorsey’s presentation on moats, Moats and Macro

Ensemble Capital’s The Death (of Many) Brands

Buffett on Economic Moats – Alpha Architect

Capital Allocation and Governance:
Mauboussin: Capital Allocation
Outsiders: Will Thorndike Interview
Tren Griffin on Outsiders

Strategic and Intangible Assets:
https://www.cfapubs.org/doi/pdf/10.2469/faj.v73.n4.4
Why Financial Statements Don’t Work for Highly Innovative Companies
http://osam.com/Commentary/negative-equity-veiled-value-and-the-erosion-of-price-to-book
-“Our proprietary process of identifying Knowledge Leaders corrects for a 1974 accounting ruling requiring firms to expense all innovative investments in the period in which they are incurred, which has given rise to a steady deterioration in the information content found in financial statements and an actionable market mispricing anomaly. To correct for this ultra-conservative accounting stance, we identify and capitalize innovative investments R&D, brand, IT, human capital development, and organizational capital for roughly 5,000 companies across the developed and emerging markets. In order to be included in a Knowledge Leaders Index and considered for our active or passive portfolios, companies must meet a set of specific criteria, including possessing a high level of intellectual property capital, high levels of profitability and lean balance sheets, all reflective of a firm executing a successful innovation strategy.”
-https://hbr.org/2018/02/why-financial-statements-dont-work-for-digital-companies
-http://blog.knowledgeleaderscapital.com/?p=35
-http://blog.knowledgeleaderscapital.com/?p=372
-http://blog.knowledgeleaderscapital.com/?p=10616
-http://blog.knowledgeleaderscapital.com/?p=7365
-http://blog.knowledgeleaderscapital.com/?p=56
-http://blog.knowledgeleaderscapital.com/?p=14005
-http://blog.knowledgeleaderscapital.com/?p=514
-http://blog.knowledgeleaderscapital.com/?p=7355
-http://blog.knowledgeleaderscapital.com/?p=593
-http://blog.knowledgeleaderscapital.com/?p=120
-http://blog.knowledgeleaderscapital.com/?p=128
-http://blog.knowledgeleaderscapital.com/?p=121
-http://blog.knowledgeleaderscapital.com/?p=14274
-http://blog.knowledgeleaderscapital.com/?p=14137
-http://www.evergage.com/blog/how-calculate-customer-churn-and-revenue-churn/

Roic/Cfroic:
Calculating Return on Invested Capital
http://basehitinvesting.com/importance-of-roic-reinvestment-vs-legacy-moats/
http://basehitinvesting.com/calculating-the-return-on-incremental-capital-investments/

Resources:

Customer Analytics, Churn:
churn-4-types
Source: KDNuggets
-Bruce Hardie’s Talks and Tutorials
http://stats.stackexchange.com/questions/20463/rfm-customer-lifetime-value-modeling-in-r
http://cdn.intechopen.com/pdfs/13162/InTech-Data_mining_using_rfm_analysis.pdf
https://cran.r-project.org/web/packages/BTYD/vignettes/BTYD-walkthrough.pdf
http://www.producao.ufrgs.br/arquivos/disciplinas/495_serv_20090518_10_journal_of_service_research_-_lifetime_value.pdf

SaaS Metrics Links:
http://www.forentrepreneurs.com/saas-metrics-2/
http://www.forentrepreneurs.com/saas-metrics/
https://www.slideshare.net/KellySchwedland/building-the-billion-dollar-saas-unicorn-ceo-guide
Startup Metrics for Pirates
Economics of Customer Businesses: Mauboussin

Tren Griffin on Unit Economics
https://25iq.com/2017/07/15/amazon-prime-and-other-subscription-businesses-how-do-you-value-a-subscriber/
https://25iq.com/2016/12/31/a-half-dozen-ways-to-look-at-the-unit-economics-of-a-business/

These five factors determine the “unit economics” of a business:

a customer acquisition cost (CAC);
an average revenue per user (ARPU);
a gross margin;
a customer lifetime (which is a function of customer retention/churn); and
a discount rate.

amzn-prime

http://www.haydencapital.com/wp-content/uploads/Hayden-Capital-Quarterly-Letter-2018-Q4.pdf

Forecasting:
https://research.fb.com/prophet-forecasting-at-scale/

Selecting Forecasting Methods in Data Science
aaeaaqaaaaaaaamqaaaajgu1mzllowi0ltu0yzktndy1mc04zwu0lwzkzgjiodmymza0mw

M4 competition results:
https://www.m4.unic.ac.cy/wp-content/uploads/2018/06/Evangelos_Spiliotis_ISF2018.pdf
https://eng.uber.com/m4-forecasting-competition/
https://eng.uber.com/forecasting-introduction/
https://www.scribd.com/document/382185710/IJF-Published-M4-Paper
https://github.com/carlanetto/M4comp2018
https://github.com/pmontman
https://github.com/M4Competition/M4-methods/blob/dd70af03aa8402fd5714f2be0f1b9fd574923f74/132%20-%20roubinchtein/allforcodef.R
https://github.com/robjhyndman/M4metalearning/blob/master/docs/metalearning_example.md
ttps://robjhyndman.com/papers/Theta.pdf
https://eng.uber.com/omphalos/
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3173287

Past Kaggle (Data Science) Competition Solutions:
–http://ndres.me/kaggle-past-solutions/
–https://www.kaggle.com/sudalairajkumar/winning-solutions-of-kaggle-competitions
–http://www.chioka.in/kaggle-competition-solutions/

http://www.capitalspectator.com/combination-forecasts/

The Capital Spectator’s combination forecasts are based on the following models:

Exponential smoothing state space model: the average forecast is used from 100 simulations based on bootstrap aggregating via the forecasting package. The data set is the historical record for the target indicator.

Autoregressive integrated moving average model: the average forecast is used from 100 simulations based on bootstrap aggregating via the forecasting package. The data set is the historical record for the target indicator.

Neural network model: the average forecast is used from 100 simulations via the forecasting package. The data set is the historical record for the target indicator.

Naïve model: this forecast simply extracts the last data point and assumes that it will prevail for the next 12 months.

Cubic Spline model: a local linear forecasts using cubic smoothing splines via the forecasting package. The data set is the historical record for the target indicator.

Facebook’s Prophet forecasting tool. The data set is the historical record for the target indicator.

Theta method forecast model: the methodology is a simple exponential smoothing with drift via the forecasting package.

Bayesian Structural Time Series: Time series regression using dynamic linear models fit using a Markov chain Monte Carlo methodology via the bsts package, which was written by Google’s Steven Scott and Hal Varian.

Vector autoregression model: this multivariate methodology (via the vars package).