diff --git a/examples/automl_example/time_series/ts_classification/pdl_example.py b/examples/automl_example/time_series/ts_classification/pdl_example.py
index eb2aec401..1b617450a 100644
--- a/examples/automl_example/time_series/ts_classification/pdl_example.py
+++ b/examples/automl_example/time_series/ts_classification/pdl_example.py
@@ -2,8 +2,8 @@
 from fedot_ind.core.repository.config_repository import DEFAULT_COMPUTE_CONFIG
 
 DATASET_NAME = 'Lightning7'
-COMPARISON_DICT = dict(pairwise_approach=['quantile_extractor', 'pdl_clf'],
-                       baseline=['quantile_extractor', 'rf'])
+COMPARISON_DICT = dict(pairwise_approach={0: ['quantile_extractor', 'pdl_clf']},
+                       baseline={0: ['quantile_extractor', 'rf']})
 METRIC_NAMES = ('f1', 'accuracy', 'precision', 'roc_auc')
 
 COMPUTE_CONFIG = DEFAULT_COMPUTE_CONFIG
@@ -32,5 +32,5 @@
         result_dict = ApiTemplate(api_config=API_CONFIG,
                                   metric_list=METRIC_NAMES).eval(dataset=DATASET_NAME,
                                                                  initial_assumption=node_list,
-                                                                 finetune=True)
+                                                                 finetune=False)
         print(f'Approach: {approach}. Metrics: {result_dict["metrics"]}')
diff --git a/fedot_ind/api/utils/checkers_collections.py b/fedot_ind/api/utils/checkers_collections.py
index 3b83fd1d2..08ae73641 100644
--- a/fedot_ind/api/utils/checkers_collections.py
+++ b/fedot_ind/api/utils/checkers_collections.py
@@ -204,10 +204,9 @@ def _check_fedot_context(self):
                 left_function=lambda x: x.features,
                 right_function=lambda strategy: self.convert_ts_method[strategy]
                 (self.input_data, self.strategy_params.get('sampling_strategy', None)))
-            if is_big_data:
-                self.input_data.features, self.input_data.target = output_data.predict, output_data.target
-            else:
-                self.input_data.features = output_data.predict
+            self.input_data.features = output_data.predict if hasattr(output_data, 'predict') else output_data
+            if is_big_data and hasattr(output_data, 'target'):
+                self.input_data.target = output_data.target
 
     def _convert_ts2tabular(self, input_data, sampling_strategy):
         if sampling_strategy is not None: