Every year someone notices Google Trends rising for “All I Want for Christmas is You”. It signals the start of the Christmas period for some. How high will it get this year?
Rather than forecast the Google Trend (complicated because the whole scale will be redone if Christmas 2021 is bigger than previous years) let’s look at the amount of traffic to the All I Want for Christmas is You wikipedia page. This data is freely available from Toolforge
Given this data from 2015 up until yesterday what will the pageviews forecast look like for this year?
Running the most basic Forecast Forge forecast looks like this:
There are a few good things here; the algorithm has clearly learned that something big happens in December and it isn’t doing anything too crazy like predicting negative values. But, it seems to me, that the algorithm is massively underestimating the scale of the “All I Want for Christmas is You”-mania that is likely to happen in 2021.
The above statement is partially me making a judgement call (I think it is possible but unlikely that the wikipedia page will see the lowest levels of traffic since 2015) ad partially me knowing that the default Forecast Forge algorithm will struggle to fit seasonalities as extreme as we see in the training data.
This kind of thing is a tradeoff that all machine learning approaches will have to make somewhere; the flexibility required to fit extreme seasonality like this would also allow the algorithm to overfit in other situations where there is random noise. Unfortunately I can’t just make a few easy tweaks behind the scenes to Forecast Forge and have it magically work for this forecast and all the others. So I’m going to have to get creative to improve things.
The first thing to do is to look at the chart and try to figure out what kind of seasonal pattern there is.
To me, it looks like there is two parts to it:
You can add regressor columns to help fit both of these patterns as long as the pattern is the same every year; to me, this looks fairly close to the truth for the sawtooth section, but less so for the extra spike.
You can easily add a sawtooth regressor by having an ascending count of days since November 1st. The count resets back to zero after December 25th and then starts again on November 1st the next year. The machine learning then makes sure that the slope of the sawtooth in the forecast is the best fit for the training data.
This looks much more like it! Now let’s add another regressor for the big spike. This is a bit more of a judgement call; I’ve added it just for December 24th and 25th but you could spread it out across more days. You could even do a “final week” sawtooth if that was a better fit for the data (the end result would be two sawtooths stacked on top of each other).
The forecast with this method is quite similar to with just the sawtooth but the extra regressor column allows for a slightly higher peak:
There is a bit more work that could be done here; Maria re-released her Merry Christmas album in 2019 which is probably why that year is so high and in 2020 she was in an Apple TV Christmas special. As far as I can figure out this will not be happening in 2021 although she has released a new collaboration with Khalid on November 5th.
Here is the output from the spreadsheet:
A quick, easier to check prediction; pageviews for the “All I Want For Christmas is You” wikipedia page will peak on 24th December close to 30k. I will check in again with how this is looking nearer the time and also show you some other forecasting methods.
In my last post I talk about how you can use a forecast to measure the impact of a some kind of change (e.g. Google rewriting your title tags in the SERP). One of the main difficulties you might find with this is that the width of the predictive interval is too wide to conclude that a change has had a positive/negative effect with XX% probability.
What do you do if your best guess is that the test has a positive outcome but you aren’t 95% sure? Will Critchlow has written about this kind of issue which they sometimes see at Search Pilot. Will has a set of recommendations they use in this situation based around the mantra “we’re doing business, not science” which is an important rule to remember (unless you are a scientist!).
On 24th August 2021 Google announced a change in how page title’s would be displayed in search results. The new system means that Google’s machine learning systems will more often display a custom page title in the links on a search engine results page; before there was less rewriting being done and the contents of the
<title> tag was more likely to be used.
Barry Schwartz has written a good summary of the ins and outs of this over at Search Engine Land.
As with any algorithm change, Google are saying that this improves results overall but there are some people for whom the new titles seem to be performing significantly worse.
If something is a lot worse or better than it was previously then you don’t need fancy statistics to be able to see that.
One of the challenging things of using a machine learning system like Forecast Forge is learning how much you can trust the results. Obviously the system isn’t 100% infallible so it is important to have an idea of where it can go wrong and how badly it can go wrong when you are talking through a forecast with your boss or clients.
One ways that people familiarise themselves with Forecast Forge is to run a few backtests. A backtest is where you make a forecast for something that has already happened and then you can compare the forecast against the actual values.
For example you might make a forecast for the first six months of 2021 using data from 2020 and earlier. Then you can compare what the forecast said would happen against the real data.
Use data from this period To predict here ________________________________________~~~~~~~~~~~~~ |------------|------------|------------|------------|--------????|????????? 2016 2017 2018 2019 2020 Then use the same methodology here
Sometimes when you do this you will see the forecast do something dumb and you will think “stupid forecast. That obviously can’t be right because we launched the new range then” or something like that - the reason will probably be very specific to your industry or website. If you can convert your reasoning here into a regressor column then you can use this to make the forecast better.
On Tuesday I was kindly invited to discuss PPC Forecasting as part of the regular #PPCchat Twitter chat. There is a recap put up on the official website.
#PPCchat started just over 10 years ago and, whilst I don’t think I was involved in the very first one I joined the conversation as soon as it was moved to a more convenient time for the UK timezone. It was a very important part of my week for a number of years but I’ve drifted away from the community as my work moved away from hands on PPC management and more towards digital analytics and data science. I was very flattered to be invited to be a guest on the chat and very happy to be able to help a community that has helped me a lot.
The twitter chat format felt a bit frantic so I thought I’d expand on some of the ideas and questions raised here.
Before getting into anything too complicated here are what I think the two most important things you can do to get better at forecasting are. They have nothing to do with machine learning or fancy techniques or anything like that; you should be able to apply them regardless of your current process.
If you do only these two things then your forecasting will start to improve. And you don’t even need to pay for a Forecast Forge subscription to do them!
To help clarify things and avoid talking at cross-purposes (always a risk on Twitter) I split forecasting up into three overlapping areas:
Type one forecasts, where you forecast the impact of something new, are a very interesting challenge; the way to approach them from a Machine Learning angle is to collect data from other people who have done the new thing and then try to figure out which of the other people your client is most similar too. This is basically what people do too when they draw on their experience to make an estimate. Forecast Forge doesn’t store your data, know anything about the sector your business is in, or know exactly what metrics you are forecasting so this is not something it supports (there are a few ways you could “hack” this - ask me if you want to test them).
Forecasting doing more or less of something that you’ve already been doing is really important for paid media; this is how you estimate the impact of increasing or decreasing your budgets which is a super-important and frequently demanded forecast for everyone.