I have a problem statement where I would like to predict the likelihood that broker will fulfill his order commitment or not.

For ex: Let's say there are 3 parties involved in this transaction and they are company A, broker A, end_customer A. Works like below

Broker A finds out that end_customer A needs 500 units of product (ex:sensors). So, broker A places/registers an order with company A for 500 units. (so he gets an early bird discount and also this prevents other brokers from placing the same order for same customer...Something Like design registration/protection). Based on this company A starts building products in stages and be happy that they will earn revenue from 500 units (Yay! big order). But what happens most of the time is, broker A only buys 100 units. This is the pain point. As company A, we would like to know why does this happen? how can we predict such behavior in advance, so we can save our production resources and also plan our revenues accordingly. For ex: If another broker B, comes in and places an order with us (company A), we would like to predict the likelihood of this transaction being fulfilled or not. By fulfill, I mean if the broker manages to order 50% (250 out of 500 above) of qty requested, we consider that as fulfilled. Again, this 50% pc is just a random number. It can be 60 pc or 70 pc as well based on business needs. IRL, 100 pc exact fulfillment has not happened in our case (90% of the time)

My dataset contains characteristics of the product such as product segment, product family etc. They also contain characteristics of the broker such as broker profile (big/small in terms of business to company A, location of broker A, market segment that broker A operates in etc., end_customer detail-location only

So, my questions are as follows

a) I have historical data of order requested and order placed. I create a rule-based labelling based on % difference between order requested and order placed. If diff > 50%, it is label 0(not fulfilled), otherwise it is label 1 (fulfilled). In future even if a very new broker comes in, I would like to predict the likelihood that whether he will meet his order requested target or not.

b) Can this problem even be modelled using ML? Do you think there are lot of external factors to this which we cannot control? So, this might impact our prediction problem. Am not interested in causal modelling. Just prediction. Do you think this problem is not amenable for ML? I ask because mostly we will be predicting outcomes for existing brokers (seen in historical data) but still do you think it is logical to predict an outcome for a brand new broker?

c) If it is not solvable using ML, what kind of additional info do you think will be good to have to solve this problem using ML?

d) If we decide to solve using ML, Am I right to understand that traditional algo like logistic, decision trees etc can be used for this classification?

e) Any other suggestions ?

  • $\begingroup$ This looks like a complicated problem, I doubt we will be able to solve it with this limited information. Anyway, I do not understand the problem, you say that the broker finds out that an end company needs 500 units of something and so places an order of 500 units to company A. But a little later you say that said broker will eventually actually buy only 100 units from company A, how is that possible? The order was for 500 units, not 100. What kind of contract is this? $\endgroup$ Jan 5, 2022 at 11:45
  • $\begingroup$ Yes, this scenario of not keeping the order commitment is very much possible.. Meaning, it can be poor planning by the end_customer. For ex: a small scale company "abcd" may order 50000 qty initially but later their end user said they don't want the product or cancelled the order (with ABCD after booking 100 units). However, a big company like Apple has lot of planning resources, experts who are good at planning and don't deviate much from their order requested qty. For ex: Apple may get 45000 out of 50000. $\endgroup$
    – The Great
    Jan 6, 2022 at 12:09
  • $\begingroup$ The reason why brokers place huge orders initially is because they get early bird discount price from Company A if they place huge orders (and this has a formal contract). Once we approve the contract, they book only 10% of order requested (and close the door). If we are to strictly force them to stick to contract, they will go to our competitors (who will give them better price or hassle free transaction (as no contract)) $\endgroup$
    – The Great
    Jan 6, 2022 at 12:12
  • $\begingroup$ OK... not a great position to be in, but I guess you know what you are doing. Anyway, as far as I understand, it's not the brokers who are not keeping their end of the deal, but rather the end companies, which initially want x amount of some product but then later reevaluate their decisions, and the brokers react to their behavior. Or is the issue related to the brokers, which "know" how much of a product an end company will need, but purposely place a higher order to get a "free" discount? $\endgroup$ Jan 7, 2022 at 8:10
  • $\begingroup$ The historical data that you mentioned, you have data on which broker placed which order for which end company? Do you have this pairing broker order-end company? Or do you only have information on the broker's orders but do not know for which end company this amount is reserved. Can a broker order some amount of the product for multiple end companies at once, so as to place a higher order and get a better deal? $\endgroup$ Jan 7, 2022 at 8:14

1 Answer 1


I have my doubts that you will be able to find anything of value from this data, because it involves market data, which is very chaotic and involves... people, which all have unknown motivations. However you should still try, you never know.

To summarize your question and comments:

  • end companies will need some amount of a certain product
  • brokers predict how much of a product end companies will need before they know it and place an order on their "behalf" (because they get a discount) to companies which produce said product
  • the brokers inevitably make a mistake with their predictions and only order a portion of the initial order (because they can, since it is not a binding contract, or rather you do not want to enforce it)
  • the company which produces the aforementioned product suffers because of this
  • you would like to predict the actual amount that the broker will eventually buy, while taking into account the fact that:
    • the broker might be making bad predictions about how much of a product an end company will need
    • the broker might place a higher than necessary order just to get a bigger discount (or maybe doesn't like the producing company)
    • the end company might not actually need said amount of product
    • the end company might not like this particular broker and obtain the product elsewhere
    • who knows what other shenanigans are happening behind closed doors

Whatever the case, in it's simplest form you can try to figure out if there is any pattern in the brokers or end companies behavior. You could try a classification model, by turning your dependent variable into a binary variable (1 for more than half the order, 0 else), or even better you could try modelling the actual numbers (or ratios).

If you have your data into a standard format for regression such as

Actually Sold Initial Order Broker End Company
100 500 A A
200 400 A B
100 600 B A

you could try your luck with any of the standard models, such as linear regression, to try and figure out if maybe there is an issue with the brokers, end companies, or both. In this case you would try to predict "Actual" based on the other variables. Of course if you have any other variables which might help in figuring this out you can definitely include them.

Alternatively you could try your luck with classification (predicting 1 or 0), if your data is in the format

Outcome Initial Order Broker End Company
1 500 A A
0 400 A B
1 600 B A

and try to predict the probability of 1 or 0 occurring (the probability of a successful transaction or not), for ex. using logistic regression.

  • $\begingroup$ I really appreciate your interest to help me and write a detailed answer. Upvoted and accepted. I am currently trying and keep you posted. I agree with you on external factors (ex: market conditions etc,) $\endgroup$
    – The Great
    Jan 10, 2022 at 13:16
  • $\begingroup$ Yes, I have the initial order and actual sold variables (along with other characteristic variables). I will label them using a rule based approach. Meaning, if difference between initial order and actual sold is greater than 50%, I mark them as label 1. else label 0. This way it becomes supervised and for future records, I can try to predict with the help of initial order and other characteristics because i will not have actual sold.. Hopefully it gives some decent outout $\endgroup$
    – The Great
    Jan 10, 2022 at 13:22
  • 1
    $\begingroup$ @TheGreat supervised learning includes both regression and classification, so both approaches that I outlined are possible, both produce predictions based on other variables. My advice, if your data is numerical (and not categorical), as is in your case, then use a regression model, do not categorize your data unnecessarily, as you will loose maybe important information this way (unless of course this categorization makes business sense). $\endgroup$ Jan 10, 2022 at 13:46
  • $\begingroup$ unfortunately, all my input variables are categorical..with multiple levels..nominal variables. except order variables...have to use logistic regression or catboost... $\endgroup$
    – The Great
    Jan 10, 2022 at 13:51
  • 1
    $\begingroup$ @TheGreat The choice between regression or classification is based on your dependent variable, so "Actually sold" or "Outcome" as I called them, and not on the input (independent) variables. Both regression and classification models can handle numerical and categorical variables. $\endgroup$ Jan 11, 2022 at 5:58

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.