Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
MOM! My algorithms SUCK
Search
Abe Stanway
September 19, 2013
Programming
15
2.6k
MOM! My algorithms SUCK
Given at Monitorama.eu 2013 in Berlin.
http://vimeo.com/75183236
Abe Stanway
September 19, 2013
Tweet
Share
More Decks by Abe Stanway
See All by Abe Stanway
Building Data Driven Organizations
astanway
1
200
A Deep Dive into Monitoring with Skyline
astanway
6
1.7k
Bring the Noise: Continuously Deploying Under a Hailstorm of Metrics
astanway
34
7.7k
Data Visualization in the Trenches
astanway
5
640
Gifs as Language
astanway
2
700
Your API is a Product
astanway
3
900
Zen and the Art of Writing Commit Logs
astanway
3
740
Other Decks in Programming
See All in Programming
オートマトン学習しろ / Do automata learning
makenowjust
3
110
rails_girls_is_my_gate_to_join_the_ruby_commuinty
maimux2x
0
180
GoのIteratorに詳しくなってしまう
inatonix
1
200
月間4.5億回再生を超える大規模サービス TVer iOSアプリのリアーキテクチャ戦略 - iOSDC2024
techtver
PRO
1
750
Hono・Prisma・AWSでGeoなAPI開発
nokonoko1203
5
650
Prompt Cachingは本当に効果的なのか検証してみた.pdf
ttnyt8701
0
520
Kotlin 2.0が与えるAndroid開発の進化
masayukisuda
1
250
暴走のウホーレン 〜想いってのはvimrcにしないと伝わらないんだぜ〜 / iosdc_japan_2024
uhooi
1
250
LR で JSON パーサーを作る / Coding LR JSON Parser
junk0612
2
180
全部見せます! クラシルリワードのSwiftTesting移行プロジェクト
uetyo
0
180
The Future of Frontend i18n : Intl.MessageFormat
sajikix
1
2.5k
Web技術を駆使してユーザーの画面を「録画」する
yukukotani
13
6.5k
Featured
See All Featured
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
166
48k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
34
1.7k
BBQ
matthewcrist
83
9.1k
The Art of Programming - Codeland 2020
erikaheidi
48
13k
Principles of Awesome APIs and How to Build Them.
keavy
125
16k
Design by the Numbers
sachag
277
19k
Building Your Own Lightsaber
phodgson
101
6k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
25
1.3k
How GitHub (no longer) Works
holman
310
140k
From Idea to $5000 a Month in 5 Months
shpigford
379
46k
Gamification - CAS2011
davidbonilla
79
4.9k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
36
1.9k
Transcript
@abestanway MOM! my algorithms SUCK
i know how to fix monitoring once and for all.
a real human physically staring at a single metric 24/7
that human will then alert a sleeping engineer when her
metric does something weird
Boom. Perfect Monitoring™.
this works because humans are excellent visual pattern matchers* *there
are, of course, many advanced statistical applications where signal cannot be determined from noise just by looking at the data.
can we teach software to be as good at simple
anomaly detection as humans are?
let’s explore.
anomalies = not “normal”
humans can tell what “normal” is by just looking at
a timeseries.
“if a datapoint is not within reasonable bounds, more or
less, of what usually happens, it’s an anomaly” the human definition:
there are real statistics that describe what we mentally approximate
None
“what usually happens” the mean
“more or less” the standard deviation
“reasonable bounds” 3σ
so, in math speak, a metric is anomalous if the
absolute value of latest datapoint is over three standard deviations above the mean
we have essentially derived statistical process control.
pioneered in the 1920s. heavily used in industrial engineering for
quality control on assembly lines.
traditional control charts specification limits
grounded in exchangeability past = future
needs to be stationary
produced by independent random variables, with well- defined expected values
this allows for statistical inference
in other words, you need good lookin’ timeseries for this
to work.
normal distribution: a more concise definition of good lookin’ μ
34.1% 13.6% 2.1% 34.1% 13.6% μ - σ 2.1%
if you’ve got a normal distribution, chances are you’ve got
an exchangeable, stationary series produced by independent random variables
99.7% fall under 3σ
μ 34.1% 13.6% 2.1% 34.1% 13.6% 2.1% μ - σ
if your datapoint is in here, it’s an anomaly.
when only .3% lie above 3σ...
...you get a high signal to noise ratio...
...where “signal” indicates a fundmental state change, as opposed to
a random, improbable variation.
a fundamental state change in the process means a different
probability distribution function that describes the process
determining when probability distribution function shifts have occurred, as early
as possible. anomaly detection:
μ 1
μ 1 a new PDF that describes a new process
drilling holes sawing boards forging steel
snapped drill bit teeth missing on table saw steel, like,
melted
processes with well planned expected values that only suffer small,
random deviances when working properly...
...and massive “deviances”, aka, probability function shifts, when working improperly.
the bad news:
server infrastructures aren’t like assembly lines
systems are active participants in their own design
processes don’t have well defined expected values
they aren’t produced by genuinely independent random variables.
large variance does not necessarily indicate poor quality
they have seasonality
skewed distributions! less than 99.73% of all values lie within
3σ, so breaching 3σ is not necessarily bad 3σ possibly normal range
the dirty secret: using SPC-based algorithms results in lots and
lots of false positives, and probably lots of false negatives as well
no way to retroactively find the false negatives short of
combing with human eyes!
how do we combat this?* *warning! ideas!
we could always use custom fit models...
...after all, as long as the *errors* from the model
are normally distributed, we can use 3σ
Parameters are cool! a pretty decent forecast based on an
artisanal handcrafted model
but fitting models is hard, even by hand.
possible to implement a class of ML algorithms that determine
models based on distribution of errors, using Q-Q plots
Q-Q plots can also be used to determine if the
PDF has changed, although hard to do with limited sample size
consenus: throw lots of different models at a series, hope
it all shakes out.
[yes] [yes] [no] [no] [yes] [yes] = anomaly!
of course, if your models are all SPC-based, this doesn’t
really get you anywhere
use exponentially weighted moving averages to adapt faster
fourier transforms to detect seasonality
second order anomalies: is the series “anomalously anomalous”?
...this is all very hard.
so, we can either change what we expect of monitoring...
...and treat it as a way of building noisy situational
awareness, not absolute directives (alerts)...
...or we can change what we expect out of engineering...
...and construct strict specifications and expected values of all metrics.
neither are going to happen.
so we have to crack this algorithm nut.
...ugh. @abestanway