Law of large numbers

Also known as "law of big numbers" or "average law ". In the long-term practice, people often find that there are almost inevitable rules in the large number of repetition of random phenomena, that is, the law of large numbers. The significance of this rule is that the larger the number of risk units, the closer the actual loss result will be to the expected loss possible result obtained from the infinite number of units. Based on this, the insurer can accurately predict risks, reasonably determine the insurance rate, and balance the insurance premiums and losses and other expenses collected within the warranty period. The law of big numbers is the mathematical foundation on which the modern insurance industry depends. Insurance companies analyze the relative stability of the loss caused by the loss of the underwriting subject based on the rule that the uncertainty in some situations will disappear in large numbers. According to the law of large numbers, the number of each type of subject matter covered by an insurance company must be large enough. Otherwise, without a certain quantity base, the required quantity rules cannot be generated. However, any insurance company has its limitations, that is, the units with the same risk nature of underwriting are limited. This requires reinsurance to expand the risk unit and risk dispersion.

It is also called "Big Data Law ". In a large number of repetitive experiments and observations of random phenomena, the general term for a type of theorem that appears almost inevitable regularity. For example, when you throw a coin, it is accidental to show the front or the back. However, after a large number of repeated throwing, the ratio of the number of Front (or back) to the total number of times must be close to the constant of 1/2. This is one of the first laws to discover large numbers.
(Supplement ):
1. "If an experiment can be repeated again and again, the probability of an event from the relative number of times will be close to the actual or theoretical probability. "