{"id":12341,"date":"2018-06-17T20:17:08","date_gmt":"2018-06-17T18:17:08","guid":{"rendered":"http:\/\/revva.net\/?p=12341"},"modified":"2023-11-23T15:43:25","modified_gmt":"2023-11-23T15:43:25","slug":"using-ai-to-forecast-sales-and-demand","status":"publish","type":"post","link":"https:\/\/imssc.org\/biflix\/using-ai-to-forecast-sales-and-demand\/","title":{"rendered":"Using AI to forecast sales and demand"},"content":{"rendered":"
\n
In a previous article about predictive analytics >><\/a><\/strong> that only a couple of close friends read, I stated that such procedure can actually convert data into money<\/span><\/span>. <\/span>This time, I bring a practical study case to\u00a0<\/span><\/span>demonstrate<\/span><\/span> that I was not overstating<\/span><\/span>. <\/span>Well, I shouldn\u2019t be demonstrating anything, as anybody working in airlines and large hotel chains had that very fact <\/span><\/span>scientifically<\/span><\/span> proven long ago<\/span><\/span>. <\/span>But <\/span><\/span>apparently<\/span><\/span> \u201clessen\u201d sectors in the travel industry still believe \u201cdata analysis\u201d is nonsensical, un-businesslike stuff reserved for the IT bunch<\/span><\/span>. Thus, this is <\/span>just<\/span><\/span> an exercise of self-affirmation more than anything else. <\/span><\/div>\n
Hope somebody find it at least <\/span><\/span>slightly<\/span><\/span> thought-provoking or useful for their own company<\/span><\/span>.<\/span><\/div>\n<\/div>\n
\n
\u00a0<\/span><\/div>\n<\/div>\n
\n

A foreword: it\u2019s not \u201cA.I.\u201d, actually<\/span><\/h4>\n<\/div>\n
\n
Apologies to the engineers and experts that might be <\/span>accidentally<\/span><\/span> reading this text. <\/span>I cringe too every time I see \u201cAI\u201d on this kind of post, but I needed some sort of click bait to get al least three or four readers from my industry<\/span><\/span>. <\/span>Let\u2019s call things by their proper name, then: what we are using to gauge our predictions is not \u201cA.I.\u201d but one of its many facets, a method called <\/span>machine learning<\/strong><\/span>. It is a flavour of intelligence because, after all, the technique involves a form of learning. We have a look at the data and, if it\u2019s good and there\u2019s enough of it, we can create a \u201cmodel\u201d that would <\/span>be used<\/span><\/span> to predict outcomes. <\/span>Then an algorithm is build (or recycled) to “perform” the prediction model, which will <\/span><\/span>be tested<\/span><\/span> in several ways and environments<\/span><\/span>. <\/span>Finally, the outcome <\/span><\/span>is verified<\/span><\/span>: either the prediction was accurate (close enough to real-life results) or wrong<\/span><\/span>. Both results are good, though, because the \u201cmachine\u201d will take note and <\/span>learn<\/span> from it, so next time it will fare better. And the next time even better, and so on. <\/span><\/div>\n
Just<\/span><\/span> like you and I should do\u2026<\/span><\/div>\n<\/div>\n
\n
\u00a0<\/span><\/div>\n<\/div>\n
\n

The subject<\/span><\/h4>\n<\/div>\n
\n
Bear in mind that a project like this can <\/span><\/span>be conducted<\/span><\/span> for <\/span>any business implementing a booking engine<\/strong><\/span>. <\/span>Our lab rat was an Italian B2B wholesaler, with data collection that goes for over a year (the bare <\/span><\/span>minimum<\/span><\/span> to get acceptable predictions)<\/span><\/span>. <\/span>Their customer backbone <\/span><\/span>is made by<\/span><\/span> loyal retailers; we focused in a few of them with enough data to check if the predictions would be reliable<\/span><\/span>. <\/span>In this study case we\u2019ll present outcomes from a <\/span>single<\/strong> agency for simplicity; our wholesaler\u2019s dashboard would include the same analysis for <\/span>all<\/strong> their clients<\/span><\/span>.<\/span><\/div>\n<\/div>\n
\n
\u00a0<\/span><\/div>\n<\/div>\n
\n

The data<\/span><\/h4>\n<\/div>\n
\n
We had to combine two datasets coming from the same database, because the vast majority of booking engines don\u2019t provide data from <\/span>searches logs<\/span>, it must <\/span><\/span>be exported<\/span><\/span> separately<\/span><\/span>. <\/span>Aside from that, the dataset size was rather small and there was no technical challenge <\/span><\/span>in terms of<\/span><\/span> ETL, <\/span><\/span>just<\/span><\/span> a few corrections here and there<\/span><\/span>. Data originated in travel-related systems is usually well structured. Alas, it\u2019s almost never <\/span>properly<\/span><\/span> stored and managed\u2026 Anyway, please note that this study\u2019s dataset goes from May 2017 to May 2018. We also used a dummy dataset, as training data. <\/span>As further testing means, sometimes we did run the algorithms \u201cbackwards\u201d (I’ll dispense with the explanation), to verify if the predictions would deliver results <\/span><\/span>similar to<\/span><\/span> the actual bookings done in past months<\/span><\/span>. It turns out they did, with an acceptable error margin.<\/span><\/div>\n<\/div>\n
\n
\u00a0<\/span><\/div>\n<\/div>\n
\n

The goal<\/span><\/h4>\n<\/div>\n
\n
We wanted to know what our loyal retailers would be buying next, spending how much, when and for which destinations<\/span><\/span>. <\/span>The main focus was on \u201cmulti\u201d trips, that is, bookings which include more than one city and\/or hotel and\/or transportation means<\/span><\/span>. <\/span>Obviously<\/span><\/span>, that\u2019s of special interest being the most profitable type of booking, but we checked all type of services bought, especially hotel + flight<\/span><\/span>.<\/span><\/div>\n<\/div>\n
\n
\u00a0<\/span><\/div>\n<\/div>\n
\n

The tools<\/span><\/h4>\n<\/div>\n
\n
Forget it, I\u2019m not going to support your DIY little project. <\/span>Besides, even if you had infinite resources available to buy all the fancy software and powerful computers, you\u2019ll need a proper data scientist to work out the right flow and use the correct algorithms (or adapt existing ones) \u2026<\/span><\/span>. <\/span>And you\u2019ll need somebody to help the data scientist come out with the right predictive model and inferences<\/span><\/span>. That would be me (call me a data executive, if you will).<\/span><\/div>\n<\/div>\n
\n
\u00a0<\/span><\/div>\n<\/div>\n
\n

The outcome<\/span><\/h4>\n<\/div>\n
\n
Once there\u2019s enough data to play with, correlations and constructs are easy to come by. Not all those would be useful, though, especially for predictive means. In short, whoever does the analysis must know what to look for (the data executive). See why getting the tools and the data scientists is not enough?<\/div>\n<\/div>\n
\n
For instructional purposes, we\u2019ll concentrate on three aspects: expectations, timelines and chances of getting \u201cmulti\u201d trips booked<\/span><\/span>.<\/span><\/div>\n
\"Expectactions<\/div>\n<\/div>\n
\n
\u00a0<\/span><\/div>\n<\/div>\n
\n
\u00b7 General expectations<\/strong>: we took total pax as an interesting figure, <\/span><\/span>perhaps<\/span><\/span> not for this study case in particular, but DMCs would definitely find it useful<\/span><\/span>. <\/span>Even more useful would be the \u201ctype of passenger\u201d graph, which was quite accurate: it shows a surge of children to <\/span><\/span>be expected<\/span><\/span> during August, which is normal for the Italian market<\/span><\/span>. Net profits expected, <\/span>on the other hand<\/span><\/span>, is a sought-after indicator. In this case it shows a negative trend, but it doesn\u2019t mean there\u2019s a problem, as we\u2019ll see on the next analysis.<\/span><\/div>\n
\"Advanced<\/div>\n<\/div>\n
\n
\u00b7 Timelines:<\/strong> there are a few fascinating findings here. <\/span>This agency usually books between one and four months before travel date, <\/span><\/span>however<\/span><\/span> it looks for dates well over a year from now\u2026 That\u2019s why the profit expectation from the previous analysis has a negative trend: they rarely book with a lot of advance, which is normal for this agency and its market<\/span><\/span>. <\/span>Besides, the analysis is a couple of months old and we did run that particular forecast up to June: if the timeline went to September\u2019s end, the trend would have been definitely positive, as August is Italy\u2019s main holyday month<\/span><\/span>. The \u201cBookings predicted and chances\u201d graph proved to be rather conservative. The surge on reservations done in March is due to Eastern\u2019s holiday, plus special summer offers. <\/span>The red line there shows the \u201cconfidence\u201d the system has in its prediction: the higher the curve, the more confident it is<\/span><\/span>. <\/span>For past months (previous to June 2018) as I mentioned predictions were conservative, because the actual number of bookings was 5% to 10% higher (except March)<\/span><\/span>. Lower confidence means that there was not enough data, in general, to be confident. Hey, it\u2019s a newborn algorithm: give the machine time to learn! Next year, with more data, it will do better. Granted!<\/span><\/div>\n
\"Multi<\/div>\n<\/div>\n
\n
\u00b7 \u201cMulti\u201d bookings:<\/strong> all the above could <\/span><\/span>be performed<\/span><\/span> specifically<\/span><\/span> for this kind of trips, of course<\/span><\/span>. <\/span>Moreover, here we compared the monthly chances of \u201cmulti\u201d trip <\/span><\/span>being booked<\/span><\/span> instead of fligh+hotel packages<\/span><\/span>. <\/span>Finally, we tried predicting how much in advance and which months would \u201cmulti\u201d trips would <\/span><\/span>be booked<\/span><\/span> with higher chances<\/span><\/span>.<\/span><\/div>\n<\/div>\n
\n
\u00a0<\/span><\/div>\n<\/div>\n
\n
I\u2019ll leave the <\/span>destination<\/span> demand forecasting results for now: there\u2019s not much sense in anticipating the preferred resorts from a single agency, but the whole customer base offers a pretty clear idea of what the market wants <\/span><\/span>in the near future<\/span><\/span>. A mesmerizing topic that deserves its own post.<\/span><\/div>\n<\/div>\n
\n
\u00a0<\/span><\/div>\n<\/div>\n
\n

Key question: are these predictions reliable?<\/span><\/h4>\n<\/div>\n
\n
Key answer: depends. <\/span>The main problem here is the amount of data: even if we have an historical of over a year of transactions, the actual number of bookings from a single agency isn\u2019t that big, so the error margin is not acceptable in some cases<\/span><\/span>. <\/span>The number of passengers booked, for instance, is a simple prediction, and if I owned a DMC I could go on with the estimated traffic to organize forthcoming transfers<\/span><\/span>. I could also <\/span>blindly<\/span><\/span> trust sales and demand forecasts done this way, if I was a hotel\u2019s revenue manager. But I wouldn\u2019t bet on charter allotment calculations, not <\/strong><\/span>yet<\/strong>. <\/span>Forecasting which type of trip will <\/span><\/span>be booked<\/span><\/span> several months in advance from historical <\/span>and<\/span> search data is tricky<\/span><\/span>. Nobody tried it as far as we know, and we couldn\u2019t find any academic content to give us guidance.<\/span><\/div>\n<\/div>\n
\n
\u00a0<\/span><\/div>\n<\/div>\n
\n
Bookings and searches transaction numbers won\u2019t be a problem when we get our dirty hands on a huge <\/span>bedbank\u2019s dataset<\/span>: they have hundreds of bookings, billions or searches <\/span>per day<\/strong><\/span>.<\/span> I am looking forward to start that project (my data boffins are salivating at the prospect!)<\/span><\/div>\n<\/div>\n
\n
\u00a0<\/span><\/div>\n<\/div>\n
\n
Back to our study case, we used a confidence interval and procedure that we esteemed valid, yet it can <\/span><\/span>be argued<\/span><\/span> that our machine learning algorithms based on training data might not be accurate enough<\/span><\/span>. <\/span>Perhaps<\/span><\/span> time-series forecasting would work better: that\u2019s something we\u2019ll try next time<\/span><\/span>. <\/span>My data boffins mentioned arcane methods such as Generalized Autoregressive Conditional Heteroskedasticity<\/em> (no kidding), Bayesian-based models<\/em>, and the like<\/span><\/span>. I\u2019ll publish our findings in due time. Bottom line:<\/span><\/div>\n<\/div>\n
\n
\u00a0<\/span><\/div>\n<\/div>\n
\n
[ctt template=”3″ link=”1d73U” via=”yes” ]Our ML predictions are so far correct qualitatively, slightly off quantitatively. No crystal ball yet but getting closer.[\/ctt]<\/div>\n<\/div>\n
\n
\u00a0<\/span><\/div>\n<\/div>\n
\n

Conclusions & a rant<\/span><\/h4>\n<\/div>\n
\n
\u00a0<\/span>Anybody working with data has a natural, inherent honesty that prevents them from presenting manufactured results or crappy interpretations<\/span><\/span>. <\/span>Besides, I run projects for my clients as if the outcomes would be vital for me, so I\u2019m not going to ice the cake, affirming that our predictions are a magic window that shows the future exactly as it will be<\/span><\/span>. <\/span>Even so, this approach is by far much more accurate<\/strong> than any of the <\/span><\/span>commonly<\/span><\/span> used methods in our industry (<\/span><\/span>namely<\/span><\/span>, Excel)<\/span><\/span>. Can you imagine <\/span>all of<\/span><\/span> the above done in spreadsheets? No, you can\u2019t. <\/span><\/div>\n
Still, hotel chains and even expensive revenue management systems are grounding their demand and sales forecasts <\/span>on historical data only<\/strong><\/span>, with age-old procedures<\/span><\/span>. It amazes me! <\/span>Eventually<\/span><\/span> the accommodation industry will update its toolbox, but tour operators and bed banks that are entering the forecasting dome should ditch simple statistical forecasting methods as the weapon of choice<\/span><\/span>. Why using a knife when you have a rail-gun available? <\/span><\/div>\n
Moreover, the beauty of modern forecasting <\/span><\/span>methodology<\/span><\/span> is that it may not <\/span><\/span>be limited<\/span><\/span>\u00a0exclusively to <\/span>endogenous data<\/span><\/span>. <\/span>How about adding to the mix weather parameters, air traffic, official arrival figures by destination, etc.? I am not speculating here; I find it <\/span><\/span>utterly<\/span><\/span> surprising they\u2019re not doing it already<\/span><\/span>!<\/span><\/div>\n<\/div>\n
\n
\u00a0<\/span><\/div>\n<\/div>\n
\n
Don\u2019t get me wrong, this is not bragging at all. <\/span>Rather, it\u2019s a half-backed cathartic effort that will not attest I\u2019m a visionary genius\u2026 Quite the opposite, it proves <\/span><\/span>I might<\/span><\/span> be making the same mistake I already made three times in my long career<\/span><\/span>. <\/span>Seems my brain machine is unable to learn that being a tech pioneer with no money to back up the marketing crap, equals very limited success, in a best-case scenario<\/span><\/span>. <\/span><\/div>\n
One day, when A.I-driven forecasting in travel businesses will be mainstream, I\u2019ll rejoice on my own silliness<\/span><\/span>. <\/span>Right now, I am getting the same puzzled looks I got back in the day, when tried to explain the benefits of an online booking engine to hoteliers<\/span><\/span>. And feeling the same damn frustration again.<\/span><\/div>\n<\/div>\n
\n
\u00a0<\/span><\/div>\n<\/div>\n
\n
Thanks for reading, excuse my rantings.<\/span><\/div>\n<\/div>\n
\n
\u00a0<\/span><\/div>\n<\/div>\n
\n
Marcello Bresin<\/em><\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

In a previous article about predictive analytics >> that only a couple of close friends read, I stated that such procedure can actually convert data into money. This time, I bring a practical study case to\u00a0demonstrate that I was not overstating. Well, I shouldn\u2019t be demonstrating anything, as anybody working in airlines and large hotel […]<\/p>\n","protected":false},"author":1,"featured_media":12344,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"content-type":"","_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_feature_clip_id":0,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_post_was_ever_published":false},"categories":[70],"tags":[81,78,76,75,79,83],"class_list":["post-12341","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-insights","tag-artificial-intelligence","tag-bedb","tag-data-analysis","tag-ds","tag-hotels","tag-predictive"],"acf":[],"yoast_head":"\nUsing AI to forecast sales and demand - BIFLIX<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/imssc.org\/biflix\/using-ai-to-forecast-sales-and-demand\/\" \/>\n<meta property=\"og:locale\" content=\"en_GB\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Using AI to forecast sales and demand - BIFLIX\" \/>\n<meta property=\"og:description\" content=\"In a previous article about predictive analytics >> that only a couple of close friends read, I stated that such procedure can actually convert data into money. This time, I bring a practical study case to\u00a0demonstrate that I was not overstating. Well, I shouldn\u2019t be demonstrating anything, as anybody working in airlines and large hotel […]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/imssc.org\/biflix\/using-ai-to-forecast-sales-and-demand\/\" \/>\n<meta property=\"og:site_name\" content=\"BIFLIX\" \/>\n<meta property=\"article:published_time\" content=\"2018-06-17T18:17:08+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-11-23T15:43:25+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/imssc.org\/biflix\/wp-content\/uploads\/2020\/09\/logo2extd.png\" \/>\n\t<meta property=\"og:image:width\" content=\"653\" \/>\n\t<meta property=\"og:image:height\" content=\"379\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"mbresin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"mbresin\" \/>\n\t<meta name=\"twitter:label2\" content=\"Estimated reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"9 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/using-ai-to-forecast-sales-and-demand\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/using-ai-to-forecast-sales-and-demand\\\/\"},\"author\":{\"name\":\"mbresin\",\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/#\\\/schema\\\/person\\\/6dfd8c578b6171400f04704434e47c7a\"},\"headline\":\"Using AI to forecast sales and demand\",\"datePublished\":\"2018-06-17T18:17:08+00:00\",\"dateModified\":\"2023-11-23T15:43:25+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/using-ai-to-forecast-sales-and-demand\\\/\"},\"wordCount\":1867,\"commentCount\":1,\"publisher\":{\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/using-ai-to-forecast-sales-and-demand\\\/#primaryimage\"},\"thumbnailUrl\":\"\",\"keywords\":[\"artificial intelligence\",\"bed banks\",\"data analysis\",\"data science\",\"hotels\",\"predictive analytics\"],\"articleSection\":[\"insights\"],\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/imssc.org\\\/biflix\\\/using-ai-to-forecast-sales-and-demand\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/using-ai-to-forecast-sales-and-demand\\\/\",\"url\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/using-ai-to-forecast-sales-and-demand\\\/\",\"name\":\"Using AI to forecast sales and demand - BIFLIX\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/using-ai-to-forecast-sales-and-demand\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/using-ai-to-forecast-sales-and-demand\\\/#primaryimage\"},\"thumbnailUrl\":\"\",\"datePublished\":\"2018-06-17T18:17:08+00:00\",\"dateModified\":\"2023-11-23T15:43:25+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/using-ai-to-forecast-sales-and-demand\\\/#breadcrumb\"},\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/imssc.org\\\/biflix\\\/using-ai-to-forecast-sales-and-demand\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/using-ai-to-forecast-sales-and-demand\\\/#primaryimage\",\"url\":\"\",\"contentUrl\":\"\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/using-ai-to-forecast-sales-and-demand\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Using AI to forecast sales and demand\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/#website\",\"url\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/\",\"name\":\"BIFLIX - No-code Marketing & Ecommerce analytics\",\"description\":\"Easy hotel data analytics\",\"publisher\":{\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/#organization\"},\"alternateName\":\"BIFLIX Analytics\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-GB\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/#organization\",\"name\":\"BIFLIX\",\"url\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/wp-content\\\/uploads\\\/2020\\\/08\\\/logo2.png\",\"contentUrl\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/wp-content\\\/uploads\\\/2020\\\/08\\\/logo2.png\",\"width\":389,\"height\":389,\"caption\":\"BIFLIX\"},\"image\":{\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.linkedin.com\\\/company\\\/biflix\\\/\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/imssc.org\\\/biflix\\\/#\\\/schema\\\/person\\\/6dfd8c578b6171400f04704434e47c7a\",\"name\":\"mbresin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/e06a2e80ec57faae04793048671973f3a6da0f2468df55e3c2c8ab579d7896f1?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/e06a2e80ec57faae04793048671973f3a6da0f2468df55e3c2c8ab579d7896f1?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/e06a2e80ec57faae04793048671973f3a6da0f2468df55e3c2c8ab579d7896f1?s=96&d=mm&r=g\",\"caption\":\"mbresin\"},\"sameAs\":[\"https:\\\/\\\/imssc.org\\\/biflix\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Using AI to forecast sales and demand - BIFLIX","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/imssc.org\/biflix\/using-ai-to-forecast-sales-and-demand\/","og_locale":"en_GB","og_type":"article","og_title":"Using AI to forecast sales and demand - BIFLIX","og_description":"In a previous article about predictive analytics >> that only a couple of close friends read, I stated that such procedure can actually convert data into money. This time, I bring a practical study case to\u00a0demonstrate that I was not overstating. Well, I shouldn\u2019t be demonstrating anything, as anybody working in airlines and large hotel […]","og_url":"https:\/\/imssc.org\/biflix\/using-ai-to-forecast-sales-and-demand\/","og_site_name":"BIFLIX","article_published_time":"2018-06-17T18:17:08+00:00","article_modified_time":"2023-11-23T15:43:25+00:00","og_image":[{"width":653,"height":379,"url":"https:\/\/imssc.org\/biflix\/wp-content\/uploads\/2020\/09\/logo2extd.png","type":"image\/png"}],"author":"mbresin","twitter_card":"summary_large_image","twitter_misc":{"Written by":"mbresin","Estimated reading time":"9 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/imssc.org\/biflix\/using-ai-to-forecast-sales-and-demand\/#article","isPartOf":{"@id":"https:\/\/imssc.org\/biflix\/using-ai-to-forecast-sales-and-demand\/"},"author":{"name":"mbresin","@id":"https:\/\/imssc.org\/biflix\/#\/schema\/person\/6dfd8c578b6171400f04704434e47c7a"},"headline":"Using AI to forecast sales and demand","datePublished":"2018-06-17T18:17:08+00:00","dateModified":"2023-11-23T15:43:25+00:00","mainEntityOfPage":{"@id":"https:\/\/imssc.org\/biflix\/using-ai-to-forecast-sales-and-demand\/"},"wordCount":1867,"commentCount":1,"publisher":{"@id":"https:\/\/imssc.org\/biflix\/#organization"},"image":{"@id":"https:\/\/imssc.org\/biflix\/using-ai-to-forecast-sales-and-demand\/#primaryimage"},"thumbnailUrl":"","keywords":["artificial intelligence","bed banks","data analysis","data science","hotels","predictive analytics"],"articleSection":["insights"],"inLanguage":"en-GB","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/imssc.org\/biflix\/using-ai-to-forecast-sales-and-demand\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/imssc.org\/biflix\/using-ai-to-forecast-sales-and-demand\/","url":"https:\/\/imssc.org\/biflix\/using-ai-to-forecast-sales-and-demand\/","name":"Using AI to forecast sales and demand - BIFLIX","isPartOf":{"@id":"https:\/\/imssc.org\/biflix\/#website"},"primaryImageOfPage":{"@id":"https:\/\/imssc.org\/biflix\/using-ai-to-forecast-sales-and-demand\/#primaryimage"},"image":{"@id":"https:\/\/imssc.org\/biflix\/using-ai-to-forecast-sales-and-demand\/#primaryimage"},"thumbnailUrl":"","datePublished":"2018-06-17T18:17:08+00:00","dateModified":"2023-11-23T15:43:25+00:00","breadcrumb":{"@id":"https:\/\/imssc.org\/biflix\/using-ai-to-forecast-sales-and-demand\/#breadcrumb"},"inLanguage":"en-GB","potentialAction":[{"@type":"ReadAction","target":["https:\/\/imssc.org\/biflix\/using-ai-to-forecast-sales-and-demand\/"]}]},{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/imssc.org\/biflix\/using-ai-to-forecast-sales-and-demand\/#primaryimage","url":"","contentUrl":""},{"@type":"BreadcrumbList","@id":"https:\/\/imssc.org\/biflix\/using-ai-to-forecast-sales-and-demand\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/imssc.org\/biflix\/"},{"@type":"ListItem","position":2,"name":"Using AI to forecast sales and demand"}]},{"@type":"WebSite","@id":"https:\/\/imssc.org\/biflix\/#website","url":"https:\/\/imssc.org\/biflix\/","name":"BIFLIX - No-code Marketing & Ecommerce analytics","description":"Easy hotel data analytics","publisher":{"@id":"https:\/\/imssc.org\/biflix\/#organization"},"alternateName":"BIFLIX Analytics","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/imssc.org\/biflix\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-GB"},{"@type":"Organization","@id":"https:\/\/imssc.org\/biflix\/#organization","name":"BIFLIX","url":"https:\/\/imssc.org\/biflix\/","logo":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/imssc.org\/biflix\/#\/schema\/logo\/image\/","url":"https:\/\/imssc.org\/biflix\/wp-content\/uploads\/2020\/08\/logo2.png","contentUrl":"https:\/\/imssc.org\/biflix\/wp-content\/uploads\/2020\/08\/logo2.png","width":389,"height":389,"caption":"BIFLIX"},"image":{"@id":"https:\/\/imssc.org\/biflix\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.linkedin.com\/company\/biflix\/"]},{"@type":"Person","@id":"https:\/\/imssc.org\/biflix\/#\/schema\/person\/6dfd8c578b6171400f04704434e47c7a","name":"mbresin","image":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/secure.gravatar.com\/avatar\/e06a2e80ec57faae04793048671973f3a6da0f2468df55e3c2c8ab579d7896f1?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/e06a2e80ec57faae04793048671973f3a6da0f2468df55e3c2c8ab579d7896f1?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/e06a2e80ec57faae04793048671973f3a6da0f2468df55e3c2c8ab579d7896f1?s=96&d=mm&r=g","caption":"mbresin"},"sameAs":["https:\/\/imssc.org\/biflix"]}]}},"jetpack_featured_media_url":"","jetpack-related-posts":[{"id":12264,"url":"https:\/\/imssc.org\/biflix\/convert-predictive-analytics-into-money\/","url_meta":{"origin":12341,"position":0},"title":"Convert predictive analytics into money","author":"mbresin","date":"27 May 2018","format":false,"excerpt":"In late 1997 I was helping some Egyptian DMC streamline operations, when terrorists stroked at Deir el-Bahri, the heartbreaking Luxor Massacre. About a year later, not one but two hurricanes (Mitch and George) broke havoc in the Caribbean, where I was operating my own DMC. In 2010 half the world\u2019s\u2026","rel":"","context":"In "insights"","block_context":{"text":"insights","link":"https:\/\/imssc.org\/biflix\/category\/insights\/"},"img":{"alt_text":"predictive analytics cycle","src":"https:\/\/i0.wp.com\/revva.net\/wp-content\/uploads\/2018\/05\/pred-anal-1024x576.png?resize=350%2C200","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/revva.net\/wp-content\/uploads\/2018\/05\/pred-anal-1024x576.png?resize=350%2C200 1x, https:\/\/i0.wp.com\/revva.net\/wp-content\/uploads\/2018\/05\/pred-anal-1024x576.png?resize=525%2C300 1.5x"},"classes":[]},{"id":12601,"url":"https:\/\/imssc.org\/biflix\/hotel-data-between-gut-instinct-analytics\/","url_meta":{"origin":12341,"position":1},"title":"Hotel data: between gut instinct and Analytics","author":"mbresin","date":"18 October 2020","format":false,"excerpt":"The clash between gut instinct and analytics in the hotel industry's data landscape is ongoing.","rel":"","context":"In "strategy"","block_context":{"text":"strategy","link":"https:\/\/imssc.org\/biflix\/category\/strategy\/"},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/imssc.org\/biflix\/wp-content\/uploads\/2019\/10\/setup_img2.png?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":12364,"url":"https:\/\/imssc.org\/biflix\/how-analytics-boost-travel-operations\/","url_meta":{"origin":12341,"position":2},"title":"How Analytics Boost Travel Operations","author":"mbresin","date":"24 June 2018","format":false,"excerpt":"The 3 key drivers to adop BI in any travel-related company, for guaranteed success","rel":"","context":"In "insights"","block_context":{"text":"insights","link":"https:\/\/imssc.org\/biflix\/category\/insights\/"},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/imssc.org\/biflix\/wp-content\/uploads\/2018\/11\/Development.png?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":12038,"url":"https:\/\/imssc.org\/biflix\/how-to-set-up-a-data-driven-culture-in-travel\/","url_meta":{"origin":12341,"position":3},"title":"How to set up a data-driven culture in Travel Companies","author":"mbresin","date":"30 April 2018","format":false,"excerpt":"Not easy, but not as difficult as it may seem. Give it a try, you need data culture!","rel":"","context":"In "insights"","block_context":{"text":"insights","link":"https:\/\/imssc.org\/biflix\/category\/insights\/"},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/imssc.org\/biflix\/wp-content\/uploads\/2019\/01\/work3.png?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/imssc.org\/biflix\/wp-content\/uploads\/2019\/01\/work3.png?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/imssc.org\/biflix\/wp-content\/uploads\/2019\/01\/work3.png?resize=525%2C300&ssl=1 1.5x"},"classes":[]},{"id":12246,"url":"https:\/\/imssc.org\/biflix\/human-obstinacy-defeats-ai-in-the-travel-arena\/","url_meta":{"origin":12341,"position":4},"title":"AI’s Struggle Against Human Tenacity in Accommodation","author":"mbresin","date":"20 May 2018","format":false,"excerpt":"Although the term has been lingering in academic and science fiction settings for over 70 years, it seems to me everybody realized two days ago that AI is the new magical panacea that will end profitability issues overnight, replacing \u201cbig data\u201d (which now sounds so 2016). As such, everybody and\u2026","rel":"","context":"In "insights"","block_context":{"text":"insights","link":"https:\/\/imssc.org\/biflix\/category\/insights\/"},"img":{"alt_text":"AI travel","src":"https:\/\/i0.wp.com\/revva.net\/wp-content\/uploads\/2018\/05\/AI-travel.png?resize=350%2C200","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/revva.net\/wp-content\/uploads\/2018\/05\/AI-travel.png?resize=350%2C200 1x, https:\/\/i0.wp.com\/revva.net\/wp-content\/uploads\/2018\/05\/AI-travel.png?resize=525%2C300 1.5x"},"classes":[]},{"id":11714,"url":"https:\/\/imssc.org\/biflix\/beginners-guide-to-self-service-analytics\/","url_meta":{"origin":12341,"position":5},"title":"Beginners’ Guide to Self-service Analytics","author":"mbresin","date":"4 March 2018","format":false,"excerpt":"","rel":"","context":"In "insights"","block_context":{"text":"insights","link":"https:\/\/imssc.org\/biflix\/category\/insights\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]}],"jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/pfiTrI-3d3","_links":{"self":[{"href":"https:\/\/imssc.org\/biflix\/wp-json\/wp\/v2\/posts\/12341","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/imssc.org\/biflix\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/imssc.org\/biflix\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/imssc.org\/biflix\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/imssc.org\/biflix\/wp-json\/wp\/v2\/comments?post=12341"}],"version-history":[{"count":0,"href":"https:\/\/imssc.org\/biflix\/wp-json\/wp\/v2\/posts\/12341\/revisions"}],"wp:attachment":[{"href":"https:\/\/imssc.org\/biflix\/wp-json\/wp\/v2\/media?parent=12341"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/imssc.org\/biflix\/wp-json\/wp\/v2\/categories?post=12341"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/imssc.org\/biflix\/wp-json\/wp\/v2\/tags?post=12341"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}