Learn more about artificialintelligence with this collection
Understanding machine learning models
Improving data analysis and decision-making
How Google uses logic in machine learning
Typically, data analysis for a complex problem is iterative. You will discover anomalies, trends, or other features of the data. Naturally, you will develop theories to explain this data. Don’t just develop a theory and proclaim it to be true. Look for evidence (inside or outside the data) to confirm/deny this theory.
105
275 reads
MORE IDEAS ON THIS
When making theories about data, we often want to assert that "X causes Y"—for example, "the page getting slower caused users to click less." You can not simply establish causation because of correlation. By considering how you would validate a theory of causation, you can usually develop a good ...
105
278 reads
Randomness exists and will fool us. Some people think, “Google has so much data; the noise goes away.” This simply isn’t true. Every number or summary of data that you produce should have an accompanying notion of your confidence in this estimate (through measures such as confidence intervals and...
112
728 reads
Especially if you are trying to capture a new phenomenon, try to measure the same underlying thing in multiple ways. Then, determine whether these multiple measurements are consistent.
By using multiple measurements, you can identify bugs in measurement or logging code, unexpected feature...
105
309 reads
The previous points suggested some ways to get yourself to do the right kinds of soundness checking and validation. But sharing with a peer is one of the best ways to force yourself to do all these things. A skilled peer can provide qualitatively different feedback than the consumers of your data...
106
293 reads
Both slicing and consistency over time are particular examples of checking for reproducibility. If a phenomenon is important and meaningful, you should see it across different user populations and time. But verifying reproducibility means more than performing these two checks. If you are building...
105
288 reads
There’s always a motivation to analyze data. Formulating your needs as questions or hypotheses helps ensure that you are gathering the data you should be gathering and that you are thinking about the possible gaps in the data. Of course, the questions you ask should evolve as you look at the data...
107
276 reads
If you create new metrics (possibly by gathering a novel data source) and try to learn something new, you won’t know if your new metric is right. With new metrics, you should first apply them to a known feature or data.
If you have a new metric for where users are directing their attention...
105
275 reads
Examine outliers carefully because they can be canaries in the coal mine that indicate more fundamental problems with your analysis.
It's fine to exclude outliers from your data or to lump them together into an "unusual" category, but you should make sure that you know why data ended up i...
116
782 reads
Not only do we typically work with very large data sets, but those data sets are extremely rich. That is, each row of data typically has many, many attributes. When you combine this with the temporal sequences of events for a given user, there are an enormous number of ways of looking at the data...
111
1.26K reads
As part of the "Validation" stage, before actually answering the question you are interested in (for example, "Did adding a picture of a face increase or decrease clicks?"), rule out any other variability in the data that might affect the experiment. For example:
105
318 reads
The most interesting metrics are ratios of underlying measures. Oftentimes, interesting filtering or other data choices are hidden in the precise definitions of the numerator and denominator. For example, which of the following does “Queries / User” actually mean?
109
345 reads
Looking at day-over-day data also gives you a sense of the variation in the data that would eventually lead to confidence intervals or claims of statistical significance. This should not generally replace rigorous confidence-interval calculation, but often with large changes you can see they will...
105
405 reads
Almost every large data analysis starts by filtering data in various stages. Maybe you want to consider only US users, or web searches, or searches with ads. Whatever the case, you must:
106
370 reads
Good data analysis will have a story to tell. To make sure it’s the right story, you need to tell the story to yourself, then look for evidence that it’s wrong. One way of doing this is to ask yourself, “What experiments would I run that would validate/invalidate the story I am telling?” Even if ...
108
276 reads
Slicing means separating your data into subgroups and looking at metric values for each subgroup separately. We commonly slice along dimensions like browser, locale, domain, device type, and so on. If the underlying phenomenon is likely to work differently across subgroups, you must slice the dat...
110
537 reads
Before looking at any data, make sure you understand the context in which the data was collected. If the data comes from an experiment, look at the configuration of the experiment. If it's from new client instrumentation, make sure you have at least a rough understanding of how the data is collec...
105
360 reads
You should almost always try slicing data by units of time because many disturbances to underlying data happen as our systems evolve over time. (We often use days, but other units of time may also be useful.)
During the initial launch of a feature or new data collection, practitioners ofte...
107
427 reads
Most practitioners use summary metrics (for example, mean, median, standard deviation, and so on) to communicate about distributions.
However, you should usually examine much richer distribution representations by generating histograms, cumulative distribution functions (CDFs), Quantile-Q...
128
923 reads
We typically define various metrics around user success.
You can not use the metric that is fed back to your system as a basis for evaluating your change. If you show more ads that get more clicks, you can not use “more clicks” as a basis for deciding that users are happier, even though “m...
106
255 reads
With a large volume of data, it can be tempting to focus solely on statistical significance or to home in on the details of every bit of data. But you need to ask yourself, "Even if it is true that value X is 0.1% more than value Y, does it matter?"
This can be especially important if you...
106
464 reads
Often you will be calculating a metric that is similar to things that have been counted in the past. You should compare your metrics to metrics reported in the past, even if these measurements are on different user populations.
You do not need to get an exact agreement, but you should be i...
105
275 reads
Validation: Do I believe the data is self-consistent, that it was collected correctly, and that it represents what I think it does?
Description: What's the objective interpretation of this data? For example, "Users make fewer queries classified as X," "In t...
112
355 reads
When doing exploratory analysis, perform as many iterations of the whole analysis as possible. Typically you will have multiple steps of signal gathering, processing, modeling, etc. If you spend too long getting the very first stage of your initial signals perfect, you are missing out on opportun...
106
267 reads
105
259 reads
Anytime you are producing new analysis code, you need to look at examples from the underlying data and how your code is interpreting those examples. Your analysis is abstracting away many details from the underlying data to produce useful summaries.
How you sample these examples is importa...
111
632 reads
When looking at new features and new data, it's particularly tempting to jump right into the metrics that are new or special for this new feature. However, you should always look at standard metrics first, even if you expect them to change.
For example, when adding a new universal block t...
105
299 reads
Read & Learn
20x Faster
without
deepstash
with
deepstash
with
deepstash
Access to 200,000+ ideas
—
Access to the mobile app
—
Unlimited idea saving & library
—
—
Unlimited history
—
—
Unlimited listening to ideas
—
—
Downloading & offline access
—
—
Personalized recommendations
—
—
Supercharge your mind with one idea per day
Enter your email and spend 1 minute every day to learn something new.
I agree to receive email updates