{"id":67,"date":"2022-02-16T09:14:51","date_gmt":"2022-02-16T08:14:51","guid":{"rendered":"http:\/\/blog.dataengineer.at\/?p=67"},"modified":"2022-02-17T21:26:19","modified_gmt":"2022-02-17T20:26:19","slug":"wie-wird-mein-umsatz-forecast-mit-machine-learning","status":"publish","type":"post","link":"http:\/\/blog.dataengineer.at\/en\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/","title":{"rendered":"How is my turnover? Forecasting with machine learning"},"content":{"rendered":"<figure class=\"wp-block-pullquote\"><blockquote><p>How will my new financial year be?<br>Can sales developments be foreseen?<\/p><\/blockquote><\/figure>\n\n\n\n<p>We can consult the Oracle!<\/p>\n\n\n\n<p>Or we use some data science magic.<\/p>\n\n\n\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_82_2 counter-hierarchy ez-toc-counter ez-toc-light-blue ez-toc-container-direction\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Inhalt<\/p>\n<label for=\"ez-toc-cssicon-toggle-item-69f50a10c6016\" class=\"ez-toc-cssicon-toggle-label\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewbox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewbox=\"0 0 24 24\" version=\"1.2\" baseprofile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/label><input type=\"checkbox\"  id=\"ez-toc-cssicon-toggle-item-69f50a10c6016\" checked aria-label=\"Toggle\" \/><nav><ul class='ez-toc-list ez-toc-list-level-1' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"http:\/\/blog.dataengineer.at\/en\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/#Prediction\" >Prediction<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"http:\/\/blog.dataengineer.at\/en\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/#Machine_Learning_fur_Dummies\" >Machine learning for dummies<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"http:\/\/blog.dataengineer.at\/en\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/#Die_Losung\" >The solution<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"http:\/\/blog.dataengineer.at\/en\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/#Ist-Zahlen\" >Actual figures<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"http:\/\/blog.dataengineer.at\/en\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/#Prediction-2\" >Prediction<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"http:\/\/blog.dataengineer.at\/en\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/#Report\" >Report<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"http:\/\/blog.dataengineer.at\/en\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/#Planung\" >Planning<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"http:\/\/blog.dataengineer.at\/en\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/#Special\" >Special<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"http:\/\/blog.dataengineer.at\/en\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/#Cloud_Architektur\" >Cloud architecture<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"http:\/\/blog.dataengineer.at\/en\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/#Conclusio\" >Conclusion<\/a><\/li><\/ul><\/nav><\/div>\n<h2 class=\"wp-block-heading\" id=\"prediction\"><span class=\"ez-toc-section\" id=\"Prediction\"><\/span>Prediction<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>There are two types of machine learning predictions: regression and classification<br>Regression predicts continuous values, so how much?<\/p>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Regression-1-1024x688.png\" alt=\"\" class=\"wp-image-589\" width=\"256\" height=\"172\" srcset=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Regression-1-1024x688.png 1024w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Regression-1-300x202.png 300w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Regression-1-768x516.png 768w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Regression-1-18x12.png 18w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Regression-1-600x403.png 600w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Regression-1-945x635.png 945w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Regression-1.png 1083w\" sizes=\"auto, (max-width: 256px) 100vw, 256px\" \/><\/figure>\n\n\n\n<p>The classification determines a group membership, so what?<\/p>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Class-1024x468.png\" alt=\"\" class=\"wp-image-588\" width=\"512\" height=\"234\" srcset=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Class-1024x468.png 1024w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Class-300x137.png 300w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Class-768x351.png 768w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Class-18x8.png 18w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Class-600x274.png 600w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Class-945x432.png 945w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Class.png 1353w\" sizes=\"auto, (max-width: 512px) 100vw, 512px\" \/><\/figure>\n\n\n\n<p>And then there is the time series, values over time, so when and how much?<\/p>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Timeseries.png\" alt=\"\" class=\"wp-image-590\" width=\"460\" height=\"274\" srcset=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Timeseries.png 613w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Timeseries-300x179.png 300w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Timeseries-18x12.png 18w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Pred_Timeseries-600x357.png 600w\" sizes=\"auto, (max-width: 460px) 100vw, 460px\" \/><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"machine-learning-fur-dummies\"><span class=\"ez-toc-section\" id=\"Machine_Learning_fur_Dummies\"><\/span>Machine learning for dummies<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<figure class=\"wp-block-pullquote\"><blockquote><p>Don't you need a data scientist for that?<\/p><\/blockquote><\/figure>\n\n\n\n<p>Eigentlich schon und sie sind hoch gesch\u00e4tzt von mir, aber f\u00fcr sehr einfache Vorhersagen mit wenigen Parametern und guten Grunddaten kann man es durchaus mit fertigen Bibliotheken versuchen &#8211; und das ist unsere &#8222;Magie&#8220;&#8230;<\/p>\n\n\n\n<p>Now how does this work?<br>Quite simple: We send in the existing actual figures for sales development and get a forecast for future figures over time.<\/p>\n\n\n\n<figure class=\"wp-block-pullquote\"><blockquote><p>Of course, this is not so easy for the machine learning method.<br>What's really happening?<\/p><\/blockquote><\/figure>\n\n\n\n<p>Various characteristics of the data are examined: <br>the trend of a longer period, <br>the seasonality, repeating patterns over time,<br>cycles of data,<br>error deviation, etc.<\/p>\n\n\n\n<p>This becomes \u2013 only the data scientist knows how \u2013 a forecast for each data point in the future.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"die-losung\"><span class=\"ez-toc-section\" id=\"Die_Losung\"><\/span>The solution<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"ist-zahlen\"><span class=\"ez-toc-section\" id=\"Ist-Zahlen\"><\/span>Actual figures<span class=\"ez-toc-section-end\"><\/span><\/h3>\n\n\n\n<p>We have a central data warehouse, where we initially have the operative actual figures, with which good reports, e.g. with moving averages can be showed.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/dwh2-teil.png\" alt=\"\" class=\"wp-image-601\" width=\"289\" height=\"338\" srcset=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/dwh2-teil.png 385w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/dwh2-teil-256x300.png 256w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/dwh2-teil-10x12.png 10w\" sizes=\"auto, (max-width: 289px) 100vw, 289px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"575\" src=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Ist_zahlen-1024x575.png\" alt=\"\" class=\"wp-image-600\" srcset=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Ist_zahlen-1024x575.png 1024w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Ist_zahlen-300x169.png 300w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Ist_zahlen-768x432.png 768w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Ist_zahlen-1536x863.png 1536w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Ist_zahlen-18x10.png 18w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Ist_zahlen-600x337.png 600w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Ist_zahlen-945x531.png 945w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Ist_zahlen.png 1605w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"prediction-1\"><span class=\"ez-toc-section\" id=\"Prediction-2\"><\/span>Prediction<span class=\"ez-toc-section-end\"><\/span><\/h3>\n\n\n\n<p>The actual data is processed in Databricks with Spark technology and Python, the predictions are calculated and saved again in our data warehouse.<\/p>\n\n\n\n<p>Since we do not want to evaluate our sales across all areas as a total, differentiation should also be possible according to the type of sale, the product group and the region.<\/p>\n\n\n\n<p>However, this also means that each combination of these must be predicted separately, so this is processed in nested loops, the actual prediction magic happens in just 4 lines.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"866\" src=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/prediction_marker-1024x866.png\" alt=\"\" class=\"wp-image-625\" srcset=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/prediction_marker-1024x866.png 1024w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/prediction_marker-300x254.png 300w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/prediction_marker-768x650.png 768w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/prediction_marker-14x12.png 14w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/prediction_marker-600x508.png 600w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/prediction_marker-945x799.png 945w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/prediction_marker.png 1143w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"report\"><span class=\"ez-toc-section\" id=\"Report\"><\/span>Report<span class=\"ez-toc-section-end\"><\/span><\/h3>\n\n\n\n<p>The actual sales can be displayed in a report together with the forecasts and a range of variation.<\/p>\n\n\n\n<p>All combinations of sales type, product group and region can be filtered in any combination.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"576\" src=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Forecast-1024x576.png\" alt=\"\" class=\"wp-image-603\" srcset=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Forecast-1024x576.png 1024w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Forecast-300x169.png 300w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Forecast-768x432.png 768w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Forecast-1536x864.png 1536w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Forecast-18x10.png 18w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Forecast-600x337.png 600w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Forecast-945x531.png 945w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Forecast.png 1608w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption>blue - actual figures \/ gray - prediction actual \/ orange - prediction future<\/figcaption><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"planung\"><span class=\"ez-toc-section\" id=\"Planung\"><\/span>Planning<span class=\"ez-toc-section-end\"><\/span><\/h3>\n\n\n\n<p>Our forecast already gives a very good impression of the future development of sales, but controlling department certainly knows better what other influencing factors and business developments are pending in the coming year.<\/p>\n\n\n\n<p>In this way, we can not only use the predictive forecast as an outlook, but also as a data basis for planning, on which any adjustments can be made.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"575\" src=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Predictive_forecast-1024x575.png\" alt=\"\" class=\"wp-image-610\" srcset=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Predictive_forecast-1024x575.png 1024w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Predictive_forecast-300x168.png 300w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Predictive_forecast-768x431.png 768w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Predictive_forecast-1536x863.png 1536w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Predictive_forecast-18x10.png 18w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Predictive_forecast-600x337.png 600w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Predictive_forecast-945x531.png 945w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Predictive_forecast.png 1606w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"special\"><span class=\"ez-toc-section\" id=\"Special\"><\/span>Special<span class=\"ez-toc-section-end\"><\/span><\/h3>\n\n\n\n<p>If we already have access to the data, we can determine customer segmentation as an additional benefit, for example, in order to get to know our sales based on customer characteristics.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"573\" src=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/customer_segments-1024x573.png\" alt=\"\" class=\"wp-image-611\" srcset=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/customer_segments-1024x573.png 1024w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/customer_segments-300x168.png 300w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/customer_segments-768x430.png 768w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/customer_segments-1536x860.png 1536w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/customer_segments-18x10.png 18w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/customer_segments-600x336.png 600w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/customer_segments-945x529.png 945w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/customer_segments.png 1608w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p>With the AI components in Power BI, further insights about our customers can be determined as an analysis tree and used as a targeted marketing basis.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"575\" src=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Tree-1024x575.png\" alt=\"\" class=\"wp-image-612\" srcset=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Tree-1024x575.png 1024w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Tree-300x168.png 300w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Tree-768x431.png 768w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Tree-1536x862.png 1536w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Tree-18x10.png 18w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Tree-600x337.png 600w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Tree-945x530.png 945w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Tree.png 1607w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"cloud-architektur\"><span class=\"ez-toc-section\" id=\"Cloud_Architektur\"><\/span>Cloud architecture<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>The solution architecture could look like this:<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"576\" src=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Finanacial_Forecast_Architektur-1024x576.png\" alt=\"\" class=\"wp-image-614\" srcset=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Finanacial_Forecast_Architektur-1024x576.png 1024w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Finanacial_Forecast_Architektur-300x169.png 300w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Finanacial_Forecast_Architektur-768x432.png 768w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Finanacial_Forecast_Architektur-1536x864.png 1536w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Finanacial_Forecast_Architektur-18x10.png 18w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Finanacial_Forecast_Architektur-600x338.png 600w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Finanacial_Forecast_Architektur-945x532.png 945w, http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Finanacial_Forecast_Architektur.png 1920w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p>A central data warehouse (Azure SQL) contains all of our necessary operational actual data, which is processed with databricks and the forecast that is determined is saved back to the DWH.<br>Optionally, a customer segmentation could also be determined with the data.<\/p>\n\n\n\n<p>A planning solution uses the predictive forecast as a basis and stores the planning data in the DWH.<\/p>\n\n\n\n<p>The Azure Data Factory serves as the data process.<\/p>\n\n\n\n<p>Actual data, machine forecasts and planning can now be displayed in Power BI reports and automatically sent as an email if required.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"conclusio\"><span class=\"ez-toc-section\" id=\"Conclusio\"><\/span>Conclusion<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>As a relatively simple cloud solution, a financial forecast with a manageable number of parameters and good basic data can add value for future financial figures and the planning process.<\/p>\n\n\n\n<p>Even without deep data science knowledge, useful results can be achieved.<\/p>\n\n\n\n<p>The solution is the usually existing data warehouse with the basic data, which is processed in databricks and a forecast is calculated with prediction libraries, which can also serve as a basis for planning.<\/p>\n\n\n\n<p>All key figures can be displayed and filtered together in a Power BI report.<\/p>\n\n\n\n<figure class=\"wp-block-pullquote\"><blockquote><p>Share your experience with a comment below!<\/p><\/blockquote><\/figure>","protected":false},"excerpt":{"rendered":"<p>How will my new financial year be?<br \/>\n Can sales developments be foreseen?<br \/>\nWe can consult the Oracle!<br \/>\n Or we use some data science magic.<\/p>","protected":false},"author":1,"featured_media":621,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[83,5,55,11,84,6,86,85,3,4],"tags":[16,44,90,42,91,33,13,88,68,87],"class_list":["post-67","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-advanced-analytics","category-azure","category-business-intelligence-bi","category-data-sience","category-databricks-spark","category-datentransformation-etl","category-financial-forecast","category-machine-learning","category-power-bi","category-sql-datenbanken","tag-azure","tag-data-factory","tag-data-science","tag-databricks","tag-financial-forecast","tag-machine-learning","tag-powerbi","tag-predictive-forecast","tag-python","tag-spark"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.5 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Wie wird mein Umsatz? Forecast mit Machine Learning - Data.Engineer BLOG<\/title>\n<meta name=\"description\" content=\"Wie wird mein neues Gesch\u00e4ftsjahr?Lassen sich Umsatzentwicklungen voraussehen? Wir k\u00f6nnen das Orakel befragen!Oder wir verwenden etwas Magie aus der Data Science.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"http:\/\/blog.dataengineer.at\/en\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Wie wird mein Umsatz? Forecast mit Machine Learning - Data.Engineer BLOG\" \/>\n<meta property=\"og:description\" content=\"Wie wird mein neues Gesch\u00e4ftsjahr?Lassen sich Umsatzentwicklungen voraussehen? Wir k\u00f6nnen das Orakel befragen!Oder wir verwenden etwas Magie aus der Data Science.\" \/>\n<meta property=\"og:url\" content=\"http:\/\/blog.dataengineer.at\/en\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/\" \/>\n<meta property=\"og:site_name\" content=\"Data.Engineer BLOG\" \/>\n<meta property=\"article:published_time\" content=\"2022-02-16T08:14:51+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2022-02-17T20:26:19+00:00\" \/>\n<meta property=\"og:image\" content=\"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Orakel3-Umsatz-1.png\" \/>\n\t<meta property=\"og:image:width\" content=\"800\" \/>\n\t<meta property=\"og:image:height\" content=\"400\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"data.engineer\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"data.engineer\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"http:\\\/\\\/blog.dataengineer.at\\\/wie-wird-mein-umsatz-forecast-mit-machine-learning\\\/#article\",\"isPartOf\":{\"@id\":\"http:\\\/\\\/blog.dataengineer.at\\\/wie-wird-mein-umsatz-forecast-mit-machine-learning\\\/\"},\"author\":{\"name\":\"data.engineer\",\"@id\":\"http:\\\/\\\/blog.dataengineer.at\\\/#\\\/schema\\\/person\\\/fe307e617b3de204775ffd3d9d8dc04a\"},\"headline\":\"Wie wird mein Umsatz? Forecast mit Machine Learning\",\"datePublished\":\"2022-02-16T08:14:51+00:00\",\"dateModified\":\"2022-02-17T20:26:19+00:00\",\"mainEntityOfPage\":{\"@id\":\"http:\\\/\\\/blog.dataengineer.at\\\/wie-wird-mein-umsatz-forecast-mit-machine-learning\\\/\"},\"wordCount\":664,\"commentCount\":0,\"publisher\":{\"@id\":\"http:\\\/\\\/blog.dataengineer.at\\\/#\\\/schema\\\/person\\\/fe307e617b3de204775ffd3d9d8dc04a\"},\"image\":{\"@id\":\"http:\\\/\\\/blog.dataengineer.at\\\/wie-wird-mein-umsatz-forecast-mit-machine-learning\\\/#primaryimage\"},\"thumbnailUrl\":\"http:\\\/\\\/blog.dataengineer.at\\\/wp-content\\\/uploads\\\/2022\\\/02\\\/Orakel3-Umsatz-1.png\",\"keywords\":[\"azure\",\"data factory\",\"data science\",\"databricks\",\"financial forecast\",\"machine learning\",\"powerbi\",\"predictive forecast\",\"python\",\"spark\"],\"articleSection\":[\"Advanced Analytics\",\"Azure\",\"Business Intelligence (BI)\",\"Data Sience\",\"Databricks \\\/ Spark\",\"Datentransformation (ETL)\",\"Financial Forecast\",\"Machine Learning\",\"Power BI\",\"SQL Datenbanken\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"http:\\\/\\\/blog.dataengineer.at\\\/wie-wird-mein-umsatz-forecast-mit-machine-learning\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"http:\\\/\\\/blog.dataengineer.at\\\/wie-wird-mein-umsatz-forecast-mit-machine-learning\\\/\",\"url\":\"http:\\\/\\\/blog.dataengineer.at\\\/wie-wird-mein-umsatz-forecast-mit-machine-learning\\\/\",\"name\":\"Wie wird mein Umsatz? Forecast mit Machine Learning - Data.Engineer BLOG\",\"isPartOf\":{\"@id\":\"http:\\\/\\\/blog.dataengineer.at\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"http:\\\/\\\/blog.dataengineer.at\\\/wie-wird-mein-umsatz-forecast-mit-machine-learning\\\/#primaryimage\"},\"image\":{\"@id\":\"http:\\\/\\\/blog.dataengineer.at\\\/wie-wird-mein-umsatz-forecast-mit-machine-learning\\\/#primaryimage\"},\"thumbnailUrl\":\"http:\\\/\\\/blog.dataengineer.at\\\/wp-content\\\/uploads\\\/2022\\\/02\\\/Orakel3-Umsatz-1.png\",\"datePublished\":\"2022-02-16T08:14:51+00:00\",\"dateModified\":\"2022-02-17T20:26:19+00:00\",\"description\":\"Wie wird mein neues Gesch\u00e4ftsjahr?Lassen sich Umsatzentwicklungen voraussehen? Wir k\u00f6nnen das Orakel befragen!Oder wir verwenden etwas Magie aus der Data Science.\",\"breadcrumb\":{\"@id\":\"http:\\\/\\\/blog.dataengineer.at\\\/wie-wird-mein-umsatz-forecast-mit-machine-learning\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"http:\\\/\\\/blog.dataengineer.at\\\/wie-wird-mein-umsatz-forecast-mit-machine-learning\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"http:\\\/\\\/blog.dataengineer.at\\\/wie-wird-mein-umsatz-forecast-mit-machine-learning\\\/#primaryimage\",\"url\":\"http:\\\/\\\/blog.dataengineer.at\\\/wp-content\\\/uploads\\\/2022\\\/02\\\/Orakel3-Umsatz-1.png\",\"contentUrl\":\"http:\\\/\\\/blog.dataengineer.at\\\/wp-content\\\/uploads\\\/2022\\\/02\\\/Orakel3-Umsatz-1.png\",\"width\":800,\"height\":400},{\"@type\":\"BreadcrumbList\",\"@id\":\"http:\\\/\\\/blog.dataengineer.at\\\/wie-wird-mein-umsatz-forecast-mit-machine-learning\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Startseite\",\"item\":\"http:\\\/\\\/blog.dataengineer.at\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Wie wird mein Umsatz? Forecast mit Machine Learning\"}]},{\"@type\":\"WebSite\",\"@id\":\"http:\\\/\\\/blog.dataengineer.at\\\/#website\",\"url\":\"http:\\\/\\\/blog.dataengineer.at\\\/\",\"name\":\"Data.Engineer BLOG\",\"description\":\"All about data...\",\"publisher\":{\"@id\":\"http:\\\/\\\/blog.dataengineer.at\\\/#\\\/schema\\\/person\\\/fe307e617b3de204775ffd3d9d8dc04a\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"http:\\\/\\\/blog.dataengineer.at\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":[\"Person\",\"Organization\"],\"@id\":\"http:\\\/\\\/blog.dataengineer.at\\\/#\\\/schema\\\/person\\\/fe307e617b3de204775ffd3d9d8dc04a\",\"name\":\"data.engineer\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"http:\\\/\\\/blog.dataengineer.at\\\/wp-content\\\/uploads\\\/2020\\\/12\\\/Oliver_Cartoon3_240x320-1-150x150.jpg\",\"url\":\"http:\\\/\\\/blog.dataengineer.at\\\/wp-content\\\/uploads\\\/2020\\\/12\\\/Oliver_Cartoon3_240x320-1-150x150.jpg\",\"contentUrl\":\"http:\\\/\\\/blog.dataengineer.at\\\/wp-content\\\/uploads\\\/2020\\\/12\\\/Oliver_Cartoon3_240x320-1-150x150.jpg\",\"caption\":\"data.engineer\"},\"logo\":{\"@id\":\"http:\\\/\\\/blog.dataengineer.at\\\/wp-content\\\/uploads\\\/2020\\\/12\\\/Oliver_Cartoon3_240x320-1-150x150.jpg\"},\"sameAs\":[\"http:\\\/\\\/dataengineer.at\"],\"url\":\"http:\\\/\\\/blog.dataengineer.at\\\/en\\\/author\\\/data-engineer\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Wie wird mein Umsatz? Forecast mit Machine Learning - Data.Engineer BLOG","description":"Wie wird mein neues Gesch\u00e4ftsjahr?Lassen sich Umsatzentwicklungen voraussehen? Wir k\u00f6nnen das Orakel befragen!Oder wir verwenden etwas Magie aus der Data Science.","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":"http:\/\/blog.dataengineer.at\/en\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/","og_locale":"en_US","og_type":"article","og_title":"Wie wird mein Umsatz? Forecast mit Machine Learning - Data.Engineer BLOG","og_description":"Wie wird mein neues Gesch\u00e4ftsjahr?Lassen sich Umsatzentwicklungen voraussehen? Wir k\u00f6nnen das Orakel befragen!Oder wir verwenden etwas Magie aus der Data Science.","og_url":"http:\/\/blog.dataengineer.at\/en\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/","og_site_name":"Data.Engineer BLOG","article_published_time":"2022-02-16T08:14:51+00:00","article_modified_time":"2022-02-17T20:26:19+00:00","og_image":[{"width":800,"height":400,"url":"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Orakel3-Umsatz-1.png","type":"image\/png"}],"author":"data.engineer","twitter_card":"summary_large_image","twitter_misc":{"Written by":"data.engineer","Est. reading time":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"http:\/\/blog.dataengineer.at\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/#article","isPartOf":{"@id":"http:\/\/blog.dataengineer.at\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/"},"author":{"name":"data.engineer","@id":"http:\/\/blog.dataengineer.at\/#\/schema\/person\/fe307e617b3de204775ffd3d9d8dc04a"},"headline":"Wie wird mein Umsatz? Forecast mit Machine Learning","datePublished":"2022-02-16T08:14:51+00:00","dateModified":"2022-02-17T20:26:19+00:00","mainEntityOfPage":{"@id":"http:\/\/blog.dataengineer.at\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/"},"wordCount":664,"commentCount":0,"publisher":{"@id":"http:\/\/blog.dataengineer.at\/#\/schema\/person\/fe307e617b3de204775ffd3d9d8dc04a"},"image":{"@id":"http:\/\/blog.dataengineer.at\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/#primaryimage"},"thumbnailUrl":"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Orakel3-Umsatz-1.png","keywords":["azure","data factory","data science","databricks","financial forecast","machine learning","powerbi","predictive forecast","python","spark"],"articleSection":["Advanced Analytics","Azure","Business Intelligence (BI)","Data Sience","Databricks \/ Spark","Datentransformation (ETL)","Financial Forecast","Machine Learning","Power BI","SQL Datenbanken"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["http:\/\/blog.dataengineer.at\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/#respond"]}]},{"@type":"WebPage","@id":"http:\/\/blog.dataengineer.at\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/","url":"http:\/\/blog.dataengineer.at\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/","name":"Wie wird mein Umsatz? Forecast mit Machine Learning - Data.Engineer BLOG","isPartOf":{"@id":"http:\/\/blog.dataengineer.at\/#website"},"primaryImageOfPage":{"@id":"http:\/\/blog.dataengineer.at\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/#primaryimage"},"image":{"@id":"http:\/\/blog.dataengineer.at\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/#primaryimage"},"thumbnailUrl":"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Orakel3-Umsatz-1.png","datePublished":"2022-02-16T08:14:51+00:00","dateModified":"2022-02-17T20:26:19+00:00","description":"Wie wird mein neues Gesch\u00e4ftsjahr?Lassen sich Umsatzentwicklungen voraussehen? Wir k\u00f6nnen das Orakel befragen!Oder wir verwenden etwas Magie aus der Data Science.","breadcrumb":{"@id":"http:\/\/blog.dataengineer.at\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["http:\/\/blog.dataengineer.at\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"http:\/\/blog.dataengineer.at\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/#primaryimage","url":"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Orakel3-Umsatz-1.png","contentUrl":"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2022\/02\/Orakel3-Umsatz-1.png","width":800,"height":400},{"@type":"BreadcrumbList","@id":"http:\/\/blog.dataengineer.at\/wie-wird-mein-umsatz-forecast-mit-machine-learning\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Startseite","item":"http:\/\/blog.dataengineer.at\/"},{"@type":"ListItem","position":2,"name":"Wie wird mein Umsatz? Forecast mit Machine Learning"}]},{"@type":"WebSite","@id":"http:\/\/blog.dataengineer.at\/#website","url":"http:\/\/blog.dataengineer.at\/","name":"Data.Engineer BLOG","description":"All about data...","publisher":{"@id":"http:\/\/blog.dataengineer.at\/#\/schema\/person\/fe307e617b3de204775ffd3d9d8dc04a"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"http:\/\/blog.dataengineer.at\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":["Person","Organization"],"@id":"http:\/\/blog.dataengineer.at\/#\/schema\/person\/fe307e617b3de204775ffd3d9d8dc04a","name":"data.engineer","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2020\/12\/Oliver_Cartoon3_240x320-1-150x150.jpg","url":"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2020\/12\/Oliver_Cartoon3_240x320-1-150x150.jpg","contentUrl":"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2020\/12\/Oliver_Cartoon3_240x320-1-150x150.jpg","caption":"data.engineer"},"logo":{"@id":"http:\/\/blog.dataengineer.at\/wp-content\/uploads\/2020\/12\/Oliver_Cartoon3_240x320-1-150x150.jpg"},"sameAs":["http:\/\/dataengineer.at"],"url":"http:\/\/blog.dataengineer.at\/en\/author\/data-engineer\/"}]}},"post_mailing_queue_ids":[],"_links":{"self":[{"href":"http:\/\/blog.dataengineer.at\/en\/wp-json\/wp\/v2\/posts\/67","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/blog.dataengineer.at\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/blog.dataengineer.at\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/blog.dataengineer.at\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/blog.dataengineer.at\/en\/wp-json\/wp\/v2\/comments?post=67"}],"version-history":[{"count":43,"href":"http:\/\/blog.dataengineer.at\/en\/wp-json\/wp\/v2\/posts\/67\/revisions"}],"predecessor-version":[{"id":643,"href":"http:\/\/blog.dataengineer.at\/en\/wp-json\/wp\/v2\/posts\/67\/revisions\/643"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/blog.dataengineer.at\/en\/wp-json\/wp\/v2\/media\/621"}],"wp:attachment":[{"href":"http:\/\/blog.dataengineer.at\/en\/wp-json\/wp\/v2\/media?parent=67"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/blog.dataengineer.at\/en\/wp-json\/wp\/v2\/categories?post=67"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/blog.dataengineer.at\/en\/wp-json\/wp\/v2\/tags?post=67"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}