;gender;age;continent;exp_ai;trust_ai;workplace_ai;risk_awareness;SVM;ANN;Linear Regression;XANN;Random_Forest;Decision_Tree;Best_Model;RT1;RT2;T1;T2;RC1;RC2;Remarks_on_Model
0;1;2;3;2;4;5;2;7;7;5;4;6;7;DT;1;1;If temperature is higher than more buns are produced.;weather, weekday, holidays, average growth, average demand;Things;production;better explenation
1;1;1;3;3;3;1;4;4;1;2;7;2;5;XANN;1;1;The AI predicted the sale of 227 buns. We sold 228 buns. ;The butcher should take into account the temp in Celcius. Hotter days = more fresh meat sold.;explations;sales;There is too much information for me to fully take in. I would need the full explanation and then a short summary of the model. 
2;2;2;3;2;3;2;4;4;2;5;4;5;3;LR;2;1;34 for 156.2 in one week is a huge difference. ;The temperature and time.;features;sales quantity;I miss a qui-square so i can check the median.
3;2;2;3;1;3;4;4;5;4;5;2;3;6;RF;1;3;It’s more;Use the number of buns ordered = number of steaks that are needed;Temperature;Number;Why temperature would have a large affect on the number sold
4;3;3;5;1;3;4;2;4;4;5;3;2;1;LR;3;3;The result doesn't really  seems  to fit the real life comsumtion, it either comes short for a lot or ir really overshot it;I don't know. We haven't made a significant factor study. This numbers are  post  experiment design. all the models just show correlations, they don't tell you if Temperature or rainfall amount are really determining factors for the decision, may as well account for the color of the storefont, for all that's worth for every ML algorithm;factors;sale;more cleaning of the dataset, minimeze the feature compilations to a manageable size for a human to explain. filter out the useless factors.
5;1;2;4;1;2;2;3;2;2;5;3;2;1;LR;2;2;The demand from the last four weeks is less than the prediction of the demand.;I think that the butcher should consider temperature ºC and mm of rainfall for planning demand.;variables;demand;I think I'm confident using linear regression model for the bun production decision without any extra explanation.
6;1;2;3;1;4;4;3;4;4;5;5;5;5;RF;1;3;.;.;dni;sprzedaż;Prostszego systemu wtedy mógłbym lepiej zrozumiec cały ssytem
7;1;2;3;1;5;5;4;2;3;1;5;6;5;RF;1;1;It differs a quite a bit (127.67), but it could be dued to a heavy factor like a specific time of the year like an Holiday.;Time of the year, day of the month and of the week, holidays, and weather.;factors;sell;My only doubt is if it's secure to use the IA, because I fear it could make some extreme and not real scenarios that badly influence the estimations. For exemple, it thinking just because it's not an holiday and heavely raining during school time that the sales could drop harder than they normally do
8;1;2;4;1;3;2;4;6;5;6;5;5;6;LR;2;2;There is not much influence in demand versus the prediction.;He should take into account the increase of demand for the buns. He can use the rate of increase to estimate the demand of steaks correctly.;demand;sales;I would want more data points to show a better graph.
9;1;2;3;3;3;4;3;5;6;4;6;6;5;RF;1;1;It doesn't, at least in a minor scale like this one.;He should take into account the average demand, the temperature (in Celsius) and the relative store size.;week days;demand;Regardind the  buns  example, I don't think that there's anything missing, so I guess I would use it with no problems.
10;2;1;3;1;4;3;4;3;2;5;5;5;3;XANN;1;1;The average demand of the last 4 weeks is subtracted from the base value (with other things) to get the prediction;Average demand of the last weeks, relative store size, weekday, month, advertising in last week and current week and average growth;features;quantity of sales;Why each feature is more or less relevant
11;2;4;3;2;2;3;2;4;2;5;6;3;3;LR;1;1;I don't know;temperature;features;sales;I don't know
12;2;2;4;5;2;3;4;6;3;5;2;3;3;RF;1;1;There is a drastic difference of the average demand and the specific predictions ;The butcher should take into account the average demand on the weekdays, the growth, and the month/weekday.;Features;Sale;I would like clearer visuals and a legend to accompany each visual explanation
13;2;2;4;2;3;3;4;5;6;5;6;6;7;DT;1;1;The overall average demand of the product is lesser than or subject to change by increasing demand than the specific prediction which aims towards a higher prediction by rating the average conditions of regular sale;Average demand and sale records;variables ;sale;Missing consideration of slow or low sale days, missing consideration of frequent or regular customer basis/reacurring sales
14;2;2;3;1;2;3;3;5;3;4;5;6;5;SVM;1;2;its greater than the predicition ;temperature, rainfall;features ;sales;general statistics such as the model's accuracy rate based on previous results
15;2;2;3;1;2;3;3;6;3;5;3;4;5;SVM;1;1;specific prediction assumes that average demand is 400 buns in last 4 weeks, while the actual demand is much lower;weekdays, months, holidays, temperature in celsius, relative stores;specific prediction;average demand;clarity in charts, for example, clear background would be better for reading data on tables
16;2;2;3;1;3;3;3;5;3;4;6;4;3;Blackbox ANN;1;3;The demand of the last 4 weeks shows that when we predict a higher number the actual need is lower and when we predict a lower number the actual need is much higher. I think it has a big influence on the quantity.;He needs to think about the some features like weekdays, holidays, temperature and also the tendence about the week or some days before to calculate the necessary amount.;features;quantity;I woukd need to learn more about the system.
17;2;2;3;1;3;3;3;4;2;5;6;6;5;XANN;1;1;average demand is greater;average demand per weekday, relative store size and temperature;features;sale;I think the model explanation shows the correct amount of information as to not overwhelm the viewer
18;2;4;3;5;4;4;2;3;6;4;4;5;5;DT;1;2;Only weekdays were included;size of store & temperature;data;sales;sales of the butchers
19;1;3;3;2;4;2;3;5;5;5;4;4;5;RF;1;2;It differs in volumes I think;accomodate my results in to his business, allowing for slower sales due to higher price points;estimators ;prediction ;A more simplistic evaluation to make it more usable 
20;1;2;3;3;4;4;3;3;2;5;6;2;3;XANN;1;1;the difference is big;average demand weekday and store size mostly;feature;sale;nothing really, it's quite clear and understandable
21;2;3;3;1;3;3;3;2;3;5;2;2;3;XANN;1;1;I dont understand the question;if they have similar selling trends then the butcher should consider the same features;features;amount;I miss an explantion of the bolded words (and abbreviations), as well as an explanation of how to interpret the influence of the features. Overall the explanation is difficult to read (both the text and the presentation/layout). I had a hard time determining what the actual difference between the models was, as they were all equally poorly explained. 
22;1;1;6;2;4;5;3;6;3;5;6;5;5;XANN;1;1;The average demand was lower than the predictions;Average demand weekday;features;sales quantity;We miss the knowledge of customer satisfaction
23;2;3;3;2;3;2;3;5;3;6;6;4;6;DT;1;1;It does because it should take into consideration the day off uoliday season the growth of the people customers that he might have .;It should take into consideration the average need over the last 4 weeks and also the growth of the need of the people .;Weather ;Product ;I dint quite understand the diagram as it shows in the second example . The algorithm is not clear enough for me .
24;2;2;3;1;3;2;4;6;2;7;6;4;5;LR;1;1;The actual demand has been sporadic compared to forecasted predictions, varying between above and below predicted demand.;The biggest variable for the butcher to consider is temperate as the impact of steaks has a similar selling curve to buns. ;Variables;Production;I feel there is enough information provided within the model to make a confident, informed decision. 
25;1;3;3;1;3;3;2;1;2;1;2;1;4;Blackbox ANN;1;1;The specific prediction is heavily influenced by the average demand of the previous 4 weeks, but not totally dependant on it. Therefore the number is different.;Weekday and average demand from the last 4 weeks. All other predictors have a minimal impact.;factors;sale;There is no explanation, but compared to the other 'overly complex' explanations, I felt this one was best. It would be better to have a little data though, but not an overwhelming amount.
26;1;2;3;1;3;4;4;2;1;1;6;3;4;Blackbox ANN;1;1;In the first prediction it seems the most off, as in the average demand seems a lot lower than the actual demand, around 300 units. The other two seem somewhat more in line. The second prediction off in ~50 units and the 3rd one in ~100 units.;the  actual demand  ;conditions;demand;Maybe an actual graph that would explain and break down the number at the end. 
27;2;2;3;1;3;3;4;3;5;5;5;3;6;DT;1;1;The prediction is not far off that of the actual sales needed from the 3rd month that was looked at for the figures.;They should follow the same method in predicting sales as the weather will also be a likely factor in the sales of steaks.;weather;sale;nothing comes to mind, i feel all relevant information is provided. 
28;1;3;3;2;3;3;4;5;4;3;3;6;5;RF;2;1;The average demand seems to balance after week 2 to the specific prediction, so the algorithm must take the average of last 3 weeks and exclude first one;He can follow the same algorith but consider the first week as non calculated, also he must take into account the holidays and rain fall since steaks are most consumed at holidays and at barbeque outside with sunny weather;factors;demant;This model has a structure that most brain can understand than the others, therefore it feels more safe to use it despite the difference of estimated and actual since through the process of time it can lead you to safer results, and since we are talking about bread and steaks that the profit margin is very big there is space to use it
29;1;3;3;1;3;3;4;6;3;5;5;6;5;XANN;2;3;I think it predicts a higher amount to cover all possibilities.;Average demand and sales for the last 4 weeks.;demand;number;The system only takes into account the weekly average demand and doesn't have human reaction to account for different situations etc.
30;1;2;3;1;4;4;3;4;2;6;5;5;5;LR;1;2;Apart from certain days of outliers or error terms, the average demand stays quite similar to the prediction but on all 3 graphs they show the same outlier for one of the day of the week.;Assuming the steak and the buns have similar selling trend or a correlation between the two, making note of the holidays in the coming 2 days as well as the rainfall in the current week, since these shows the greatest match, for instance, how close the holidays are to the current day, they can work out how much we should be expecting to sell.;factors;sales;More data to be injected into the model would make me feel more confident and some trial data as well as to show whether they should the corresponding number of buns as suggested 
31;1;2;6;2;4;2;3;1;1;5;6;3;2;XANN;1;1;The specific prediction shows negative influence, whereas the overall influence shows huge impact on the number of bun prediction.;The month and weekday of the sale.;factors;sales;I'd love to see how they arrive at the result, step by step in order to be convinced that the model can be used as a support system.
32;1;2;3;1;3;3;3;5;4;6;6;5;6;LR;1;1;it appears that the average demand in the last 4 weeks is higher than this specific predictions so i would say that the overall influence isn't very high;he should take account the temperature ,average demand, store size, hoildays ;circumstances;sales;i chose this system because i belive that we can easily have a linear correlations between the data that would allow us ti have an accurate prediction
33;1;2;3;1;3;4;2;4;2;5;7;6;6;XANN;1;1;The average demand is related to the other factors considered. Thus the average demand of the last 4 weeks is taken as a high weighing factor but augmented with other factors that influence demand. Thus the influence of the average demand of the last 4 weeks differs in that it is put within a context of other factors that decide the specific prediction.;Giving as much related input data as possible, such as holidays, weather, rain predictions. All factors which might influence people to buy or not buy steak. A large dataset of relevant information should be provided.;factors;sale;How the algorithm decides the average impact of each factor on the output magnitude and how reliable this weighted impact is if the dataset provided is small
34;1;2;3;1;3;3;3;3;4;5;6;6;6;XANN;1;1;The average demand of the last 4 weeks overestimates the specific prediction of bun sales. ;The butcher should also take into account his relative store size, and the temperature in Celsius. ;variables;sales;I think the model explanation is missing more information in the results section, where the graphical representation of the data could be explained in more detail - e.g. what does it mean by positive and negative influence? Also, what do the different lengths of variables on the positive/negative scale mean?
35;2;3;3;1;3;3;2;6;2;3;5;2;4;Blackbox ANN;2;2;its increased by 300, school holidays,w rm weather and normal amount of rain ;the weather, of sunny get items sorted for BBQ food, school holidays ;situations;demand;i find this confusing
36;1;3;3;1;2;3;3;2;4;3;3;4;4;DT;1;1;Other factors influence the decision to a much lesser degree actual average of demand is less;I m not sure;Factors ;Selling;[deleted, due to GDPR]
37;1;3;3;1;5;5;3;5;3;6;3;3;3;LR;2;1;Unsure,;Previous sales, same as buns and other factors such as general amounts of meat sold, daily trends (weekend vs weekday etc);temperatures;number;I did not realise this system does not take into account some much more important factors
38;2;2;3;1;3;3;4;6;3;5;6;6;6;XANN;1;1;It's a lot higher than the specific prediction;Days of the week, holidays, temperature, average demand, months;features;sales quantity;More data, more thorough explanation
39;2;1;3;1;2;3;3;5;2;5;4;6;4;RF;1;3;It’s higher;Average number of customers each day;Sale quantity ;Production ;
40;1;3;3;1;4;4;3;5;5;5;3;5;6;Blackbox ANN;1;3;It differs a lot ;It's not very clear to me;Average;Request;I would need easier explanations as these models are quite abstract and hard to understand
41;1;2;3;1;3;3;3;1;2;2;5;4;2;XANN;1;1;The overall influence of the average demand of the last 4 weeks is greater than in the specific prediction ;Primarily average weekday demand (over the last 4 weeks) followed by relative store size, then temperature in Celcious, so on and so forth;variables;sales;Further explanation as to how the specific prediction is derived from the different features. Overall the the language for all explanations is far too technical for a layman to make any sort of informed decision on which model to use.
42;2;4;3;1;3;3;2;5;4;3;5;2;2;Blackbox ANN;3;3;i would expect, using data provided that demand would be higher than predicted;demand in previous weeks;factors;sale;outside factors such as weather and temperature
43;1;2;3;3;4;4;3;4;3;5;5;5;6;DT;1;1;probably alot because of the last 4 weeks differ they can see the difference;Probably buther needs to see for the future demand the average demand weekday from last 4 weeks;features;sales quantity;it was ok
44;1;2;3;1;3;3;3;5;2;3;6;6;6;Blackbox ANN;1;1;The specific demand figures seem to be an average to what the average demand shows on the table. This means that in week 1 you will have an overstock of product, whereas in week 2 and 3 you will have an understock.;The average growth on a weekly basis and also the time of year.;principles;amount;an explanation would make this model a strong support system
45;2;4;3;1;3;3;3;5;3;4;5;4;5;DT;1;1;too small pictures to answear with certanity;Average demand, weather, holidays, advertising;principles;number;I can not answear with certainity.
46;2;4;3;3;3;3;1;3;1;5;6;6;6;DT;1;1;2 weeks we sold less than predicted so more wastage than want  final week 8 more than predicted so reasonable estimate ;recent average demand   month year on year comparison   weekday;variables;sales demand;Would prefer that equivalent year-month (eg Jun20 v Jun19) data comparison included  With stronger reference to weekday impact also 
47;1;1;3;4;4;5;3;4;2;2;2;4;4;DT;1;1;It increases from the specific prediction;The day of the week, the month, and the size of his store;features;sales;Concise information on the second photo and what the chart is showing instead of just the number 0.2,0.4 etc
48;2;2;3;1;3;3;3;3;2;3;4;4;4;RF;1;1;it was lower;Temperature, time of the year, and historical sales;average;sale;A more basic vocabulary and some more definitions. It was alot of information at once and it was hard to workout what different things meant. I think I understood it, but there was a high level of guessing as well due to being unsure of meanings.
49;1;2;3;1;2;2;2;3;2;6;6;5;4;XANN;1;1;It differs by around 20.;He could use the average demand the past 4 weeks, the holidays, and the advertising.;Days;sales;I would like for it to be a year round dataset, would make it so seasonal fluctuations with vacations would be easy to prepare for.
50;2;2;3;1;3;3;3;5;2;2;6;6;4;XANN;1;1;The average demand on weekday 3 is 345 where as the actual demand is 236.3.;Weekdays, holidays, school holidays, temperature and rainfall.;features;demand;positive and negative influence
51;1;3;3;3;2;2;3;5;3;5;4;4;6;DT;1;3;the trend is followed to predict the futures sell ;He shold analyze the trend of the others week to determinate how to proceed;predictions;stock;i miss to see the operational working in the concrete case. in fact one thing is tehory and another is practice. With some help and direct understandings that should be right btw
52;2;2;3;1;3;3;3;6;2;7;4;5;6;LR;3;1;dont know. ;the butcher should take into account the predicted temperature, the amount of advertising and the rain fall when estimating demand. ;weathers;demand ;all models lacked information on how many were produced in the other weeks and what amount of buns were wasted. 
53;1;2;3;1;4;4;5;3;3;7;3;6;6;LR;3;1;More extreme;Holidays, temperature, average demand;Parameters;Demand;Not enough examples and numbers to interpret