elasticsearch/docs/reference/search/rank-eval.asciidoc

[[search-rank-eval]]
=== Ranking Evaluation API

Allows you to evaluate the quality of ranked search results over a set of 
typical search queries.

[[search-rank-eval-api-request]]
==== {api-request-title}

`GET /<index>/_rank_eval`

`POST /<index>/_rank_eval`


[[search-rank-eval-api-desc]]
==== {api-description-title}

The ranking evaluation API allows you to evaluate the quality of ranked search 
results over a set of typical search queries. Given this set of queries and a
list of manually rated documents, the `_rank_eval` endpoint calculates and
returns typical information retrieval metrics like _mean reciprocal rank_,
_precision_ or _discounted cumulative gain_.

Search quality evaluation starts with looking at the users of your search 
application, and the things that they are searching for. Users have a specific 
_information need_; for example, they are looking for gift in a web shop or want 
to book a flight for their next holiday. They usually enter some search terms 
into a search box or some other web form. All of this information, together with 
meta information about the user (for example the browser, location, earlier 
preferences and so on) then gets translated into a query to the underlying 
search system.

The challenge for search engineers is to tweak this translation process from 
user entries to a concrete query, in such a way that the search results contain 
the most relevant information with respect to the user's information need. This 
can only be done if the search result quality is evaluated constantly across a 
representative test suite of typical user queries, so that improvements in the 
rankings for one particular query don't negatively affect the ranking for 
other types of queries.

In order to get started with search quality evaluation, you need three basic
things:

. A collection of documents you want to evaluate your query performance against, 
  usually one or more indices.
. A collection of typical search requests that users enter into your system.
. A set of document ratings that represent the documents' relevance with respect
  to a search request.
  
It is important to note that one set of document ratings is needed per test 
query, and that the relevance judgements are based on the information need of 
the user that entered the query.

The ranking evaluation API provides a convenient way to use this information in 
a ranking evaluation request to calculate different search evaluation metrics. 
This gives you a first estimation of your overall search quality, as well as a 
measurement to optimize against when fine-tuning various aspect of the query 
generation in your application.


[[search-rank-eval-api-path-params]]
==== {api-path-parms-title}

`<index>`::
 (Required, string) Comma-separated list or wildcard expression of index names
 used to limit the request.

[[search-rank-eval-api-query-params]]
==== {api-query-parms-title}

include::{es-repo-dir}/rest-api/common-parms.asciidoc[tag=allow-no-indices]
+
Defaults to `true`.

include::{es-repo-dir}/rest-api/common-parms.asciidoc[tag=expand-wildcards]
+
--
Defaults to `open`.
--

include::{es-repo-dir}/rest-api/common-parms.asciidoc[tag=index-ignore-unavailable]


[[search-rank-eval-api-example]]
==== {api-examples-title}

In its most basic form, a request to the `_rank_eval` endpoint has two sections:

[source,js]
-----------------------------
GET /my_index/_rank_eval
{
    "requests": [ ... ], <1>  
    "metric": { <2>
      "mean_reciprocal_rank": { ... } <3>
   }
}
-----------------------------
// NOTCONSOLE

<1> a set of typical search requests, together with their provided ratings
<2> definition of the evaluation metric to calculate
<3> a specific metric and its parameters

The request section contains several search requests typical to your 
application, along with the document ratings for each particular search request.

[source,js]
-----------------------------
GET /my_index/_rank_eval
{
    "requests": [
        {
            "id": "amsterdam_query", <1>
            "request": { <2>
                "query": { "match": { "text": "amsterdam" }}
            },
            "ratings": [ <3> 
                 { "_index": "my_index", "_id": "doc1", "rating": 0 },
                 { "_index": "my_index", "_id": "doc2", "rating": 3},
                 { "_index": "my_index", "_id": "doc3", "rating": 1 }
            ]
        },
        {
            "id": "berlin_query",
            "request": {
                "query": { "match": { "text": "berlin" }}
            },
            "ratings": [
                { "_index": "my_index", "_id": "doc1", "rating": 1 }
            ]
        }
    ]
  }
-----------------------------
// NOTCONSOLE

<1> the search request's id, used to group result details later 
<2> the query that is being evaluated
<3> a list of document ratings, each entry containing the document's `_index` and 
`_id` together with the rating of the document's relevance with regard to this 
search request

A document `rating` can be any integer value that expresses the relevance of the 
document on a user-defined scale. For some of the metrics, just giving a binary 
rating (for example `0` for irrelevant and `1` for relevant) will be sufficient, 
while other metrics can use a more fine-grained scale.


===== Template-based ranking evaluation

As an alternative to having to provide a single query per test request, it is 
possible to specify query templates in the evaluation request and later refer to 
them. This way, queries with a similar structure that differ only in their 
parameters don't have to be repeated all the time in the `requests` section. 
In typical search systems, where user inputs usually get filled into a small 
set of query templates, this helps make the evaluation request more succinct.

[source,js]
--------------------------------
GET /my_index/_rank_eval
{ 
   [...]
  "templates": [
     {
        "id": "match_one_field_query",  <1>
        "template": { <2>
            "inline": { 
                "query": { 
                  "match": { "{{field}}": { "query": "{{query_string}}" }}
                }
            }
        }
     }
  ], 
  "requests": [
      {
         "id": "amsterdam_query",
         "ratings": [ ... ],
         "template_id": "match_one_field_query", <3>
         "params": { <4>
            "query_string": "amsterdam",
            "field": "text"
          }
     },
    [...]
}
--------------------------------
// NOTCONSOLE

<1> the template id 
<2> the template definition to use
<3> a reference to a previously defined template
<4> the parameters to use to fill the template


===== Available evaluation metrics

The `metric` section determines which of the available evaluation metrics 
will be used. The following metrics are supported:

[float]
[[k-precision]]
===== Precision at K (P@k)

This metric measures the proportion of relevant results in the top k search results.
It's a form of the well-known
https://en.wikipedia.org/wiki/Evaluation_measures_(information_retrieval)#Precision[Precision]
metric that only looks at the top k documents. It is the fraction of relevant
documents in those first k results. A precision at 10 (P@10) value of 0.6 then
means 6 out of the 10 top hits are relevant with respect to the user's
information need.

P@k works well as a simple evaluation metric that has the benefit of being easy
to understand and explain. Documents in the collection need to be rated as either
relevant or irrelevant with respect to the current query. P@k is a set-based
metric and does not take into account the position of the relevant documents
within the top k results, so a ranking of ten results that contains one
relevant result in position 10 is equally as good as a ranking of ten results
that contains one relevant result in position 1.

[source,console]
--------------------------------
GET /twitter/_rank_eval
{
    "requests": [
    {
        "id": "JFK query", 
        "request": { "query": { "match_all": {}}},
        "ratings": []  
    }],
    "metric": {
      "precision": {
        "k" : 20,
        "relevant_rating_threshold": 1,
        "ignore_unlabeled": false
      }
   }
}
--------------------------------
// TEST[setup:twitter]

The `precision` metric takes the following optional parameters

[cols="<,<",options="header",]
|=======================================================================
|Parameter |Description
|`k` |sets the maximum number of documents retrieved per query. This value will act in place of the usual `size` parameter 
in the query. Defaults to 10. 
|`relevant_rating_threshold` |sets the rating threshold above which documents are considered to be
"relevant". Defaults to `1`.
|`ignore_unlabeled` |controls how unlabeled documents in the search results are counted.
If set to 'true', unlabeled documents are ignored and neither count as relevant or irrelevant. Set to 'false' (the default), they are treated as irrelevant.
|=======================================================================


[float]
[[k-recall]]
===== Recall at K (R@k)

This metric measures the total number of relevant results in the top k search
results. It's a form of the well-known
https://en.wikipedia.org/wiki/Evaluation_measures_(information_retrieval)#Recall[Recall]
metric. It is the fraction of relevant documents in those first k results
relative to all possible relevant results. A recall at 10 (R@10) value of 0.5 then
means 4 out of 8 relevant documents, with respect to the user's information
need, were retrieved in the 10 top hits.

R@k works well as a simple evaluation metric that has the benefit of being easy
to understand and explain. Documents in the collection need to be rated as either
relevant or irrelevant with respect to the current query. R@k is a set-based
metric and does not take into account the position of the relevant documents
within the top k results, so a ranking of ten results that contains one
relevant result in position 10 is equally as good as a ranking of ten results
that contains one relevant result in position 1.

[source,console]
--------------------------------
GET /twitter/_rank_eval
{
    "requests": [
    {
        "id": "JFK query",
        "request": { "query": { "match_all": {}}},
        "ratings": []
    }],
    "metric": {
      "recall": {
        "k" : 20,
        "relevant_rating_threshold": 1
      }
   }
}
--------------------------------
// TEST[setup:twitter]

The `recall` metric takes the following optional parameters

[cols="<,<",options="header",]
|=======================================================================
|Parameter |Description
|`k` |sets the maximum number of documents retrieved per query. This value will act in place of the usual `size` parameter
in the query. Defaults to 10.
|`relevant_rating_threshold` |sets the rating threshold above which documents are considered to be
"relevant". Defaults to `1`.
|=======================================================================


[float]
===== Mean reciprocal rank

For every query in the test suite, this metric calculates the reciprocal of the 
rank of the first relevant document. For example, finding the first relevant 
result in position 3 means the reciprocal rank is 1/3. The reciprocal rank for 
each query is averaged across all queries in the test suite to give the 
https://en.wikipedia.org/wiki/Mean_reciprocal_rank[mean reciprocal rank].

[source,console]
--------------------------------
GET /twitter/_rank_eval
{
    "requests": [
    {
        "id": "JFK query", 
        "request": { "query": { "match_all": {}}},
        "ratings": []  
    }],
    "metric": {
        "mean_reciprocal_rank": {
            "k" : 20,
            "relevant_rating_threshold" : 1
        }
    }
}
--------------------------------
// TEST[setup:twitter]

The `mean_reciprocal_rank` metric takes the following optional parameters

[cols="<,<",options="header",]
|=======================================================================
|Parameter |Description
|`k` |sets the maximum number of documents retrieved per query. This value will act in place of the usual `size` parameter 
in the query. Defaults to 10.
|`relevant_rating_threshold` |Sets the rating threshold above which documents are considered to be
"relevant". Defaults to `1`.
|=======================================================================


[float]
===== Discounted cumulative gain (DCG)

In contrast to the two metrics above, 
https://en.wikipedia.org/wiki/Discounted_cumulative_gain[discounted cumulative gain] 
takes both the rank and the rating of the search results into account.

The assumption is that highly relevant documents are more useful for the user 
when appearing at the top of the result list. Therefore, the DCG formula reduces 
the contribution that high ratings for documents on lower search ranks have on 
the overall DCG metric.

[source,console]
--------------------------------
GET /twitter/_rank_eval
{
    "requests": [
    {
        "id": "JFK query", 
        "request": { "query": { "match_all": {}}},
        "ratings": []  
    }],
    "metric": {
       "dcg": {
            "k" : 20,
            "normalize": false
       }
    }
}
--------------------------------
// TEST[setup:twitter]

The `dcg` metric takes the following optional parameters:

[cols="<,<",options="header",]
|=======================================================================
|Parameter |Description
|`k` |sets the maximum number of documents retrieved per query. This value will act in place of the usual `size` parameter 
in the query. Defaults to 10.
|`normalize` | If set to `true`, this metric will calculate the https://en.wikipedia.org/wiki/Discounted_cumulative_gain#Normalized_DCG[Normalized DCG].
|=======================================================================


[float]
===== Expected Reciprocal Rank (ERR)

Expected Reciprocal Rank (ERR) is an extension of the classical reciprocal rank 
for the graded relevance case (Olivier Chapelle, Donald Metzler, Ya Zhang, and 
Pierre Grinspan. 2009. 
http://olivier.chapelle.cc/pub/err.pdf[Expected reciprocal rank for graded relevance].)

It is based on the assumption of a cascade model of search, in which a user 
scans through ranked search results in order and stops at the first document 
that satisfies the information need. For this reason, it is a good metric for 
question answering and navigation queries, but less so for survey-oriented 
information needs where the user is interested in finding many relevant 
documents in the top k results.

The metric models the expectation of the reciprocal of the position at which a 
user stops reading through the result list. This means that a relevant document
in a top ranking position will have a large contribution to the overall score. 
However, the same document will contribute much less to the score if it appears 
in a lower rank; even more so if there are some relevant (but maybe less relevant) 
documents preceding it. In this way, the ERR metric discounts documents that 
are shown after very relevant documents. This introduces a notion of dependency 
in the ordering of relevant documents that e.g. Precision or DCG don't account 
for.

[source,console]
--------------------------------
GET /twitter/_rank_eval
{
    "requests": [
    {
        "id": "JFK query", 
        "request": { "query": { "match_all": {}}},
        "ratings": []  
    }],
    "metric": {
       "expected_reciprocal_rank": {
            "maximum_relevance" : 3,
            "k" : 20
       }
    }
}
--------------------------------
// TEST[setup:twitter]

The `expected_reciprocal_rank` metric takes the following parameters:

[cols="<,<",options="header",]
|=======================================================================
|Parameter |Description
| `maximum_relevance` | Mandatory parameter. The highest relevance grade used in the user-supplied
relevance judgments.
|`k` | sets the maximum number of documents retrieved per query. This value will act in place of the usual `size` parameter
in the query. Defaults to 10.
|=======================================================================


===== Response format

The response of the `_rank_eval` endpoint contains the overall calculated result 
for the defined quality metric, a `details` section with a breakdown of results 
for each query in the test suite and an optional `failures` section that shows 
potential errors of individual queries. The response has the following format:

[source,js]
--------------------------------
{
    "rank_eval": {
        "metric_score": 0.4, <1>
        "details": {  
            "my_query_id1": { <2>
                "metric_score": 0.6, <3>
                "unrated_docs": [ <4>
                    {
                        "_index": "my_index",
                        "_id": "1960795"
                    }, [...]
                ],
                "hits": [
                    {
                        "hit": { <5>
                            "_index": "my_index",
                            "_type": "page",
                            "_id": "1528558",
                            "_score": 7.0556192
                        },
                        "rating": 1
                    }, [...]
                ],
                "metric_details": { <6>
                    "precision" : {
                        "relevant_docs_retrieved": 6,
                        "docs_retrieved": 10
                    }
                }
            },
            "my_query_id2" : { [...] }
        },
        "failures": { [...] }
    }
}
--------------------------------
// NOTCONSOLE

<1> the overall evaluation quality calculated by the defined metric
<2> the `details` section contains one entry for every query in the original `requests` section, keyed by the search request id
<3> the `metric_score` in the `details` section shows the contribution of this query to the global quality metric score
<4> the `unrated_docs` section contains an `_index` and `_id` entry for each document in the search result for this
query that didn't have a ratings value. This can be used to ask the user to supply ratings for these documents
<5> the `hits` section shows a grouping of the search results with their supplied ratings
<6> the `metric_details` give additional information about the calculated quality metric (e.g. how many of the retrieved
documents were relevant). The content varies for each metric but allows for better interpretation of the results