Beeline Data School, for managers



    Hello Megamind!

    Until now, we taught analysts at the School of Data, taught how to use machine learning methods to solve practical problems. However, almost any practical task starts with a business need and a business setting.

    We will not talk about the fact that at the dawn of big data it was believed that the main insights and applications of analytics come more from data. This certainly exists, but in our practice this happens in the ratio of 80 to 20, where 80 percent of all tasks for the analyst or even more are born from the business.

    However, how does a business generate these tasks if it, the business, does not understand data analytics? Yes, very simple. In our company, we spent some time explaining to the business the possibilities of data analytics and now different departments are filling us with orders, coming up with new applications for these tools.

    On the other hand, data and their analytics, once the prerogative of exceptionally large companies, now penetrate everywhere, and even in startups today they often think about what to do with this data.

    How to use data to personalize offers and create an individual product, how to deal with outflows or minimize non-payment risks, how to use analytics to choose the right location for a store, how to segment company employees to select motivational schemes or predict layoffs, how to effectively recommend products, how profile clients how to work with programmatic advertising.

    All these questions more and more often arise in different areas of business along with others. For example, a company has a lot of data, for example, because it works with data from telematic devices: what to do with this data, how to make money with it? Or how to make a data-driven company so that all decisions are made based on data: where to start?

    Previously, everyone was chasing cases: the successful use of analytics to solve business problems. But, the fact is that each business is quite unique and what works for some may not work for others, but on the other hand, the success of any case is in the details, and no one will tell you these details and, again, from business to business just these details can vary significantly.

    Therefore, you will have to invent all the successful analytics applications in your business yourself. And in order to successfully do this, you need to know about the capabilities and limitations of this very analytics, and to you, as business owners, and employees of your units, since most of the applications will be generated by them, as close as possible to business tasks.

    At the same time, it is important to understand not only the applications of analytics, but also how this analytics works, as well as the problem statement. How long does it take to build a model, what data is needed, what accuracy is achievable, what accuracy is required taking into account the business sense?

    Consider this simple example: you predict a call to a call center, or fraud, or another rare event. Suppose that you need to receive a list of candidates for this event once a day, in the case of calls for early contact with your customers, and in the case of fraud to suppress it.

    Suppose your analysts made you a model with a false positive classification rating of a call or fraud of 10%. This means that with a 10% probability, a client who was not going to call the call center will be classified as being collected, and a client who did not commit fraud as a fraud.

    At the same time, suppose that the probability of a correct classification of those who call the call center or make a fraud is 87%.

    At first glance, the model is not bad. You save a lot of money by reducing the number of calls to the call center or fraud in 87% of cases. At the same time, falsely you classify those who were not going to call or make fraud in only 10% of cases.

    However, we can recall that a call to the call center per day is relatively rare event relative to the entire customer base, however, like fraud, in a normal situation. Suppose that these actions in one way or another concern 1% of all customers, which is pretty close to the truth.

    Meanwhile, our error of 10% must be applied to 99% of the entire customer base. Let's say you have 1 million customers. Then, it turns out that you contact a day in order to prevent a call to the call center or refuse to service on the basis of suspicion of fraud 1 million * 99% * 10% = 99,000 customers. And if your base is 10 million customers? And if 100?

    It turns out that such accuracy does not suit you at all and you prefer to sacrifice the accuracy of guessing those who really call, so as to underestimate as much as possible the errors of false inclusion in the forecast of those who would not call. Because these two values ​​are interconnected.

    Consider another example. You want analysts to build you an outflow model. First of all, it will be necessary to agree on what is considered an outflow. In most cases, customers clearly do not inform the company that they have left, they simply stop using the services. Accordingly, if they have not used your services for 2 weeks, is this an outflow? What about a month? What about two? This must be discussed in advance, because what you define as the target variable, then your model will predict.

    And at what point should the model predict the departure into the outflow? At the time when the client has not been using the service for a month? Or at the beginning of this period, or perhaps in advance, so that you have time to contact the client and try to keep him?

    These and many other subtleties determine the success or failure of the application of data analytics in each case.

    There are even more global questions: where in the company’s organizational structure there should be a subdivision for working with analytics, should it be a subdivision or it can be scattered among different functions, what should the subdivision's organizational structure be for it to be most effective, what processes are needed, what roles .

    In order to answer you all these and other similar questions, we have done a data analytics course for managers,Data MBA .

    In this course we talk about all the basic tools for data analysis, as well as about their application in different areas of the business using specific cases, the intricacies associated with this, the possibilities and limitations, the processes, technologies and much more necessary for successful Using data analytics to solve business problems.

    The first lesson is February 16th, recording until February 12th. No special pre-training is required, we will tell you everything in the classroom. You can sign up here .

    Also popular now: